define-evidence-protocol
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and YAML schemas. No executable scripts, binaries, or platform-level tool calls are included.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted inputs such as research questions and evidence scopes. While it lacks explicit sanitization or boundary markers, the absence of executable tools or network capabilities within the skill mitigates the risk to a negligible level.
Audit Metadata