credible-claims
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation-based framework for research discipline. It does not contain executable scripts, network requests, or privilege escalation attempts.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a protocol for processing external research data, which is an ingestion surface. However, the methodology mandates evidence-based reporting ("Require evidence, not confident conclusions") and explicit escalation triggers for the user, which act as procedural controls against potential instruction overrides in external data.
Audit Metadata