meta-reviewing-ai-reviewing
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides security guidelines for reviewing model API calls and prompt construction. It focuses on identifying vulnerabilities in target code rather than introducing them.- [PROMPT_INJECTION]: Documentation in
examples/core.mdincludes a mention of instruction overrides as an example of a pattern to be avoided. This is an educational reference to a common attack vector and does not constitute a malicious attempt to influence the agent.- [EXTERNAL_DOWNLOADS]: The skill references a metadata schema on the vendor's (agents-inc) GitHub repository. This is a legitimate vendor resource.
Audit Metadata