managing-diffmap-repo
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to manage GitHub repository activities, which involves ingesting untrusted data from issue reports and pull request comments.
- Ingestion points: The agent reads content from GitHub issues and pull requests to generate replies and descriptions.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore potentially malicious instructions embedded within the user-provided issue or PR text.
- Capability inventory: The skill utilizes
agent-browserfor screenshots and the GitHub CLI (gh) for merging pull requests and managing branches. - Sanitization: There are no explicit instructions for sanitizing, escaping, or validating the external content before it is processed or incorporated into the agent's output.
Audit Metadata