git-pull-requests
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by reading pull request bodies from GitHub. If these bodies contain malicious instructions, they could potentially influence the agent's behavior when it subsequently edits the content to update checkboxes.
- Ingestion points: The skill uses
gh pr view 57 --json body -q .body > /tmp/body.mdinSKILL.mdto fetch remote content. - Capability inventory: The skill possesses the capability to execute shell commands (
git,gh) and modify remote repository metadata. - Sanitization: No sanitization, validation, or boundary markers are defined for the content retrieved from the pull request body.
- [COMMAND_EXECUTION]: The skill executes multiple shell commands using
gitandgh(GitHub CLI) to manage branches and pull requests. These operations are core to the skill's functionality but involve executing logic based on the state of an external repository.
Audit Metadata