investigate-anything

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill package consists entirely of documentation (Markdown files) outlining professional investigative tradecraft and source evaluation techniques.
  • [NO_CODE]: There are no executable scripts (Python, Node.js, Shell), binaries, or automated processes contained within the skill. It functions as a structured prompt and reference guide for the agent.
  • [PROMPT_INJECTION]: No malicious instructions or bypasses were detected. The skill includes explicit instructions for the agent to verify ethical and legal authorization before proceeding with any investigation.
  • [DATA_EXFILTRATION]: No network operations or data harvesting mechanisms are present. While the skill mentions external selectors (emails, domains), it does so in a methodological context rather than providing code to access them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 11:53 AM
Security Audit — agent-trust-hub — investigate-anything