find-anyone
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly documentation-based and does not include any executable code, scripts, or package installations.
- [PROMPT_INJECTION]: The instructions involve processing untrusted data from external sources, presenting an inherent surface for indirect prompt injection. 1. Ingestion points: External websites and registries identified in the source catalogue. 2. Boundary markers: None provided in the methodology. 3. Capability inventory: References various OSINT tools for data aggregation. 4. Sanitization: Focuses on verification logic rather than input sanitization.
- [SAFE]: No obfuscation, data exfiltration patterns, or persistence mechanisms were found. The skill emphasizes transparency and provenance in research.
Audit Metadata