session-logs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE] (SAFE): The skill accesses conversation history stored in
~/.openclaw/. This access is necessary for its primary purpose of analyzing past sessions and does not involve exfiltration to external domains. - [COMMAND_EXECUTION] (SAFE): It provides shell snippets for processing logs. These commands use standard, non-malicious utilities such as
jq,rg,awk, andsorton local files. - [INDIRECT_PROMPT_INJECTION] (LOW):
- Ingestion points: Reads conversation history from
.jsonlfiles. - Boundary markers: None identified; the agent processes the logs as raw data.
- Capability inventory: Uses shell processing and data extraction commands.
- Sanitization: None; it acts as a search and retrieval tool.
- Note: While historical data could contain malicious prompts, this is a standard risk for any history-searching tool and does not escalate the severity.
Audit Metadata