investigate-without-getting-made
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists exclusively of Markdown documentation and reference guides. It does not include any executable scripts, binaries, or automated configuration files.
- [SAFE]: The content provides guidance on maintaining investigator anonymity and protecting attribution surfaces (IP, browser fingerprint, etc.). It includes strong emphasis on ethical boundaries and legal compliance.
- [PROMPT_INJECTION]: The skill identifies surfaces for indirect prompt injection, as it involves the agent processing data from external, untrusted sources during investigations. It provides mitigations for these risks, such as using passive archive routes and compartmented research environments.
Audit Metadata