kbn-github
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
ghCLI and GitHub API to perform actions such as creating pull requests, managing issues, and posting comments. These are legitimate capabilities required for the skill's purpose.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process external data from GitHub, which could contain instructions intended to influence the agent's behavior. \n - Ingestion points: Untrusted data enters the context via
gh pr view,gh pr diff, andgh apicalls that retrieve pull request bodies, comments, and issue descriptions as seen inSKILL.mdandreferences/review.md.\n - Boundary markers: The instructions lack explicit delimiters or specific warnings for the agent to ignore instructions embedded within the GitHub content it processes.\n
- Capability inventory: The agent has the authority to perform various state-changing operations, including creating and modifying issues and pull requests via
gh api(POST/PATCH) andghCLI commands across all files.\n - Sanitization: No sanitization, validation, or filtering mechanisms are described for the content retrieved from external sources before it is interpreted or used in subsequent operations.
Audit Metadata