ethics-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified in the instructional content.
- [NO_CODE]: The skill is purely informational/instructional markdown and does not include any scripts, binary files, or configuration for external package managers.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze research protocols, which are externally provided and potentially untrusted data. This establishes a surface for indirect prompt injection (Category 8c), although the risk is low as the agent only generates text appraisals.
Audit Metadata