dotnet-code-review
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted code from pull requests and patches.
- Ingestion points: Processes pull requests and patches in .NET repositories as defined in the trigger and workflow sections of SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or "ignore instructions" warnings when processing the provided code, which may allow an agent to inadvertently follow malicious instructions embedded in comments or code within a PR.
- Capability inventory: The skill is intended for agents that perform code analysis, review, and potentially remediation, which may involve file system access or execution of project-specific tools.
- Sanitization: There is no explicit requirement to sanitize or validate the content of the ingested code snippets before the agent processes them.
Audit Metadata