docs-from-prs
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain instructions intended to manipulate agent behavior during the documentation generation process.
- Ingestion points: Pull request titles and bodies are fetched via the
gh pr listcommand inSKILL.md(Step 1). - Boundary markers: The instructions do not provide explicit delimiters or warnings to the agent to disregard instructions potentially embedded within the PR content.
- Capability inventory: The skill has the capability to write to local documentation files (Step 5), commit changes, and create new pull requests (Step 7) using
gitandghtools. - Sanitization: There is no explicit sanitization or escaping of the PR content performed before it is interpolated into documentation files, though a general copy-editing pass is described in Step 6.
- [COMMAND_EXECUTION]: The skill utilizes several CLI tools to interact with the repository and perform its tasks.
- Executes
gh pr list,gh repo view, andgh pr createto interface with GitHub's platform. - Executes
git log,git show,git checkout,git add, andgit commitfor local repository management and change tracking. - Employs
grepfor searching source code and documentation to identify drift and verify content state. - [EXTERNAL_DOWNLOADS]: The skill fetches metadata and code status from GitHub's official services via the
ghtool. These operations are limited to a well-known service and are standard for development workflows.
Audit Metadata