receiving-pr-reviews
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runto executegh(GitHub CLI) commands. This is the primary mechanism for its functionality, and the commands are constructed using static strings or validated parameters like PR numbers and thread IDs. - [EXTERNAL_DOWNLOADS]: The skill downloads PR data and comments from GitHub's official API via the
ghtool. These operations target official GitHub infrastructure and do not include the execution of arbitrary remote code. - [REMOTE_CODE_EXECUTION]: Static analysis of the Python scripts confirms that they do not dynamically execute remote code. All logic is focused on parsing JSON output from the GitHub CLI and formatting it for the agent's context.
- [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The network operations are limited to authenticated GitHub API calls to manage the repository's own PR reviews.
- [PROMPT_INJECTION]: The
SKILL.mdcontains purely instructional workflow steps for the agent and does not attempt to bypass safety filters or override system instructions. - [DYNAMIC_EXECUTION]: The skill does not use runtime code generation or unsafe deserialization of untrusted data.
Audit Metadata