session-logs
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Employs shell pipelines with
jq,rg, andawkto process session data. - [DATA_EXFILTRATION]: Accesses personal conversation history stored in
~/.openclaw/agents/<agentId>/sessions/. While this path is specific to the agent framework, it contains sensitive user data. - [PROMPT_INJECTION]: Processing historical data creates an attack surface for indirect prompt injection.
- Ingestion points: Session logs in
~/.openclaw/agents/<agentId>/sessions/*.jsonl. - Boundary markers: Absent; no delimiters are used when extracting text from logs.
- Capability inventory: Shell command execution via
jqandrgfor data processing. - Sanitization: None; historical content is read directly without filtering.
Audit Metadata