engineer-to-founder
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill instructions and metadata found no evidence of malicious patterns, prompt injections, or unauthorized data access attempts. The instructions are consistent with the stated purpose of assisting technical founders.
- [INDIRECT_PROMPT_INJECTION]: The skill includes an ingestion point for untrusted data via a validation script, which represents a potential surface for indirect prompt injection.
- Ingestion points:
scripts/check-output.pyreads content from file paths provided as arguments. - Boundary markers: Absent.
- Capability inventory: No dangerous operations; the script is restricted to reading local files and checking for the presence of specific substrings. No network or subprocess capabilities exist.
- Sanitization: Absent.
Audit Metadata