session-investigator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- SAFE (SAFE): No malicious patterns, remote downloads, or credential exposures were detected. The skill correctly utilizes standard system utilities (jq, cat, mv) for local file analysis and diagnostic purposes.
- Indirect Prompt Injection (LOW): While the skill processes session history files containing untrusted user-provided content, the use of jq filters on structured data provides inherent protection against command injection. The file modification commands (e.g., truncation) are presented as legitimate recovery steps for interrupted agent sessions.
Audit Metadata