draft-investor-update
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a 'No secrets in context' rule as a non-negotiable principle, which explicitly instructs all spawned agents to avoid including credentials, API keys, tokens, or PII in prompts, messages, or output files. This is a strong security best practice.
- [SAFE]: The skill performs stack detection by reading standard project manifests such as package.json, requirements.txt, and Cargo.toml. This is a routine operation for context-aware developer tools and does not involve unauthorized data access.
- [SAFE]: The multi-agent architecture utilizes a 'Dual-Skeptic' review process (Accuracy and Narrative skeptics). This design effectively mitigates risks of hallucination or errors in the final output by requiring independent validation of all factual claims against project evidence.
Audit Metadata