cursor-make-pr-easy-to-review
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard developer CLI tools, including
gitandgh(GitHub CLI), to fetch Pull Request metadata, inspect commit history, and verify tree states. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external sources.
- Ingestion points: The agent ingests PR titles, descriptions, and commit messages from user-supplied URLs or branches via the
gh pr viewcommand andgitlogs. - Boundary markers: The instructions do not define explicit boundary markers or delimiters to isolate untrusted PR content from the agent's instructions.
- Capability inventory: The skill is restricted to repository management via
gitandgh, lacking capabilities for network exfiltration of sensitive files or arbitrary code execution outside the git context. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from Pull Requests before it is processed by the agent.
Audit Metadata