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, and sort to 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
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:32 AM
Security Audit — agent-trust-hub — session-logs