CVE-2026-56833: PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal
PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal Summary PraisonAI's Dynamic Context module provides filesystem-backed history and terminal-log storage. The SDK reference describes the module as providing: - artifact storage for tool outputs, history, and terminal logs; - history persistence with search; and - terminal session logging.
Published Jun 18, 2026 · Updated Jul 20, 2026
Affected packages
praisonai
- Ecosystem
- PyPI
- Affected
- >= 3.8.1, <= 4.6.58
- Fixed in
- 4.6.59
- Check
pip show praisonai
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal
Summary
PraisonAI's Dynamic Context module provides filesystem-backed history and terminal-log storage. The SDK reference describes the module as providing:
- artifact storage for tool outputs, history, and terminal logs;
- history persistence with search; and
- terminal session logging.
The module also exports agent-callable tool factories:
create_history_tools()returnshistory_search,history_tail, andhistory_get.create_terminal_tools()returnsterminal_tail,terminal_grep, andterminal_commands.
Those tools accept run_id and agent_id arguments from the tool caller. The underlying stores join those values into filesystem paths without rejecting absolute paths or .. traversal:
history_dir = self.base_dir / run_id / "history"
return history_dir / f"{agent_id}.jsonl"terminal_dir = self.base_dir / run_id / "terminal"
return terminal_dir / f"{agent_id}.log"Because run_id can be an absolute path and agent_id can contain traversal, a lower-trust prompt/user that can call these tools can read .jsonl and .log files outside the configured Dynamic Context base directory.
Affected Product
- Repository:
MervinPraison/PraisonAI - Ecosystem:
pip - Package:
praisonai - Component: Dynamic Context history and terminal tools
- Current source paths:
src/praisonai/praisonai/context/history_store.pysrc/praisonai/praisonai/context/terminal_logger.py- Latest PyPI version validated:
4.6.58 - Current
origin/mainvalidated:1ad58ca02975ff1398efeda694ea2ab78f20cf3e - Current
origin/maintag validated:v4.6.58
Suggested affected range:
pip:praisonai >= 3.8.1, <= 4.6.58Representative local sweep:
3.8.1: vulnerable4.0.0: vulnerable4.5.113: vulnerable4.6.33: vulnerable4.6.34: vulnerable4.6.40: vulnerable4.6.50: vulnerable4.6.58: vulnerable
Root Cause
HistoryStore._get_history_path() and TerminalLogger._get_log_path() treat logical identifiers as path segments, but never validate that the resolved path stays under base_dir.
History path construction:
def _get_history_path(self, run_id: str, agent_id: str) -> Path:
history_dir = self.base_dir / run_id / "history"
history_dir.mkdir(parents=True, exist_ok=True)
return history_dir / f"{agent_id}.jsonl"Terminal path construction:
def _get_log_path(self, run_id: str, agent_id: str) -> Path:
terminal_dir = self.base_dir / run_id / "terminal"
terminal_dir.mkdir(parents=True, exist_ok=True)
return terminal_dir / f"{agent_id}.log"The agent tools pass caller-controlled run_id and agent_id directly into these helpers:
def history_tail(agent_id: str = "default", run_id: str = "default", count: int = 10) -> str:
messages = history_store.get_last_messages(agent_id=agent_id, run_id=run_id, count=count)def terminal_tail(agent_id: str = "default", run_id: str = "default", lines: int = 50) -> str:
return term_logger.tail_session(agent_id=agent_id, run_id=run_id, lines=lines)There is no check equivalent to:
resolved = candidate.resolve()
base = self.base_dir.resolve()
resolved.relative_to(base)There is also no identifier allowlist preventing /, \, or .. in run_id or agent_id.
Local PoV
Run against the latest PyPI package:
uv run --with 'praisonai==4.6.58' \
python poc/pov_prai_cand_027_history_terminal_tools_path_traversal.py --jsonThe PoV:
- Creates a temporary Dynamic Context base directory.
- Creates a separate outside directory containing
secret.jsonlandsecret.log. - Creates legitimate in-base history and terminal log controls.
- Calls
history_tail()andhistory_get()withrun_id=<outside-dir>andagent_id=../secret. - Calls
terminal_tail()andterminal_grep()with the same traversal. - Confirms the traversal paths resolve to files outside the configured base.
Observed output summary from evidence/pov-pypi-4.6.58.json:
{
"package": "praisonai",
"package_version": "4.6.58",
"controls": {
"valid_history_read_works": true,
"valid_terminal_read_works": true,
"outside_history_file_outside_base_dir": true,
"outside_terminal_file_outside_base_dir": true,
"traversal_history_path_resolves_to_outside_file": true,
"traversal_terminal_path_resolves_to_outside_file": true
},
"outside_history_tail": "Last 1 messages:\\n\\n[system]: PRAI-CAND-027-HISTORY-SECRET",
"outside_terminal_tail": "PRAI-CAND-027-TERMINAL-SECRET\\nsecond line\\n",
"outside_terminal_grep": "Found 1 matches:\\n\\n--- Line 1 ---\\n> PRAI-CAND-027-TERMINAL-SECRET\\n second line",
"vulnerable": true
}The PoV is local-only. It does not start a server, contact a third-party target, or use real credentials.
Why This Is Not Intended Behavior
This report does not claim that history and terminal helpers should be unable to read legitimate history or terminal logs. The issue is narrower: logical run_id and agent_id values can escape the configured Dynamic Context base directory.
The controls show the intended boundary:
- legitimate in-base history remains readable;
- legitimate in-base terminal logs remain readable;
- the outside
.jsonland.logfiles are not under the configuredbase_dir; and - the tools still disclose those outside files through traversal identifiers.
The official context reference describes history persistence and terminal logging as filesystem-backed Dynamic Context features. The context security documentation also treats absolute paths, path traversal, and sensitive files as privacy/security risks. Reading files outside the configured context store conflicts with that documented boundary.
Impact
If a PraisonAI application exposes these Dynamic Context tools to untrusted or lower-trust prompts, the lower-trust caller can read files outside the configured context storage when the target file can be reached with the tool-imposed suffix:
history_*tools can disclose reachable.jsonlfiles;terminal_*tools can disclose reachable.logfiles; and- cross-run or cross-agent context/history/logs can be disclosed if their path is known or guessable.
This can expose conversation history, prompts, terminal output, command logs, tokens, API keys, cloud credentials, operational data, or other secrets stored in JSONL/log files readable by the PraisonAI process.
The impact is confidentiality-only in the tested surface. Integrity and availability are not claimed for this report.
Severity
Suggested severity: High.
Rationale:
AV: applies when an application exposes an agent with these tools over a network chat/API surface.AC: the traversal needs only chosenrun_idandagent_idvalues.PR: an unauthenticated or public-facing agent endpoint can be exploited without an account. Deployments that require authenticated chat/API access may score this asPR:L.UI: the attacker directly supplies the prompt/tool argument to the exposed agent surface.C: conversation history and terminal logs can contain secrets and private operational data.I:N/A: this report demonstrates read-only disclosure.
Remediation
Treat run_id and agent_id as logical identifiers, not path components.
Recommended fixes:
- Reject absolute paths, path separators, and traversal components in
run_idandagent_id. - Build candidate paths, call
.resolve(), and reject any path that is not underself.base_dir.resolve(). - Apply the same containment helper to history append/read/search/clear/export and terminal log/read/search/clear/export paths.
- Prefer opaque server-generated run and agent IDs in tool schemas.
- Add regression tests for absolute
run_id,../inrun_id, and../inagent_idfor history and terminal tool factories.
Minimal containment shape:
def _safe_child(self, *parts: str) -> Path:
candidate = self.base_dir.joinpath(*parts).resolve()
base = self.base_dir.resolve()
try:
candidate.relative_to(base)
except ValueError as exc:
raise PermissionError("Context path is outside configured base_dir") from exc
return candidatePair this with an identifier allowlist, because run_id and agent_id should not need filesystem syntax.
Credited to rexpository.
References
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
More PyPI vulnerabilities
All PyPI entriesCVE-2026-61438
PraisonAI vulnerable to Remote Code Execution via Broken AST Sandbox
high7.3Oct 29, 2026CVE-2026-60085
PraisonAI: SecurityPolicy command/path/import restrictions are completely unenforced by the default SubprocessSandbox backend
high8.7Oct 8, 2026CVE-2026-60086
PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked
medium5.3Oct 8, 2026CVE-2026-60088
PraisonAI: Project custom command templates can read outside-workspace files into model prompts
medium5.5Oct 8, 2026CVE-2026-60090
PraisonAI: PGVector and Cassandra knowledge stores interpolate vector dimensions into DDL
mediumOct 8, 2026CVE-2026-60091
PraisonAI: Jobs API is unauthenticated by default and allows attacker-controlled webhook SSRF
high7.2Oct 8, 2026
