dotnet-mcaf-human-review-planning
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a documentation and planning tool with no evidence of malicious instructions or safety guideline bypasses.
- [DATA_EXPOSURE]: The skill reads code from the repository to identify risk areas. This data access is localized and necessary for generating a human review plan. No network exfiltration or credential harvesting was identified.
- [COMMAND_EXECUTION]: The skill writes a markdown file (
HUMAN_REVIEW_PLAN.md) to the local file system. This is a standard documentation operation and does not involve arbitrary command execution or privilege escalation. - [PROMPT_INJECTION]: The skill analyzes external code, representing an ingestion point for untrusted data. However, the skill provides analysis for a human reviewer rather than executing the code, and there are no instructions to override agent safety protocols.
Audit Metadata