github
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of
ghCLI commands to perform operations on GitHub repositories, including viewing, creating, and merging pull requests and issues (inSKILL.md). - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (GitHub pull requests, issues, and API responses) which could contain malicious instructions aimed at overriding agent behavior.
- Ingestion points: Data is fetched using
gh pr view,gh issue list, andgh apicommands (inSKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of PRs or issues.
- Capability inventory: The skill possesses write capabilities, such as
gh pr mergeandgh issue close, which could be triggered by instructions embedded in the data being processed (inSKILL.md). - Sanitization: No evidence of input sanitization or validation of the content retrieved from GitHub was found.
Audit Metadata