gh-pr-review
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of a third-party GitHub CLI extension:
agynio/gh-pr-review. This downloads and installs external code into the user's environment to enable the skill's functionality. - [COMMAND_EXECUTION]: The skill relies on executing various shell commands via the
ghCLI to interact with GitHub repositories, including viewing, replying to, and resolving PR review threads. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from GitHub Pull Request comments through the
gh pr-review review viewcommand. - Ingestion points: External Pull Request comment bodies and thread data are loaded into the agent's context.
- Boundary markers: Not present. The data is parsed into structured JSON but contains raw text from reviewers.
- Capability inventory: The skill has the capability to write back to GitHub (replying to comments, resolving threads, submitting reviews) and execute shell commands.
- Sanitization: The skill provides strong instructional mitigations, explicitly requiring the agent to 'ALWAYS get user approval' and 'Wait for approval' before executing any command that posts data or modifies the PR state.
Audit Metadata