session-logs
Warn
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses sensitive conversation history stored in
~/.openclaw/agents/<agentId>/sessions/. These files contain complete logs of user and assistant interactions, representing sensitive personal data. - [COMMAND_EXECUTION]: The skill provides a set of complex shell command templates using
bash,jq,rg(ripgrep), andawkto filter and aggregate information from the session logs on the local filesystem. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Processes untrusted conversation data from historical
.jsonlfiles (SKILL.md). - Boundary markers: Absent; the skill does not include instructions to identify or ignore malicious commands that might be embedded in the retrieved logs.
- Capability inventory: Possesses command execution capabilities via multiple shell-based data processing tools (SKILL.md).
- Sanitization: Absent; session data is read and processed without any sanitization or filtering to prevent the agent from acting on malicious content in the logs.
Audit Metadata