open-a-pr
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data when reading or writing pull request bodies and descriptions.\n
- Ingestion points: Pull request bodies and descriptions provided by users or existing in the repository (SKILL.md).\n
- Boundary markers: Absent; there are no instructions for the agent to treat PR content as data only or to ignore potential instructions embedded within it.\n
- Capability inventory: The skill uses
gh pr create,gh pr edit, andgh workflow runto perform actions in the GitHub repository (SKILL.md).\n - Sanitization: Absent; the content is placed into a temporary file and used in CLI commands without explicit sanitization or validation rules.\n- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) to automate pull request workflows, including creating/editing PRs and triggering specific GitHub Actions workflows.
Audit Metadata