session-logs
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [DATA_EXPOSURE]: The skill is designed to access and read conversation history stored in
~/.openclaw/agents/<agentId>/sessions/. This contains full transcripts of previous user and assistant interactions. - [COMMAND_EXECUTION]: The skill provides various bash command templates using
jq,rg,awk, andsortto process log files. These are standard tools used for its intended purpose of log analysis. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (past session logs) which could contain malicious instructions from previous conversations.
- Ingestion points: Files located in
~/.openclaw/agents/<agentId>/sessions/*.jsonl. - Boundary markers: None identified; data is processed directly via shell utilities.
- Capability inventory: The skill employs shell command execution for searching and filtering text.
- Sanitization: There is no explicit sanitization of the content extracted from logs before it is processed or presented to the agent.
Audit Metadata