api-review
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill processes external, potentially untrusted data from GitHub issues, comments, and implementation pull requests.
- Ingestion points: As described in
SKILL.md, the skill reads the "originating issue and all comments" as well as implementation changes. - Boundary markers: The skill does not explicitly define delimiters for the ingested content to differentiate it from the agent's instructions, which is a common security consideration for agents processing user-generated content.
- Capability inventory: The skill possesses the capability to create new issues and modify pull request descriptions within the
dotnet/aspnetcorerepository. - Sanitization: The skill mitigates risks by instructing the agent not to invent information and requiring that all substantive claims be mapped to direct quotes from the source materials.
Audit Metadata