get-pr-comments
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh api) to fetch data from repositories. Variables for the command are extracted from a user-provided URL, allowing the agent to perform GitHub API operations based on user input. - [PROMPT_INJECTION]: The skill processes untrusted PR comments which creates an indirect prompt injection surface.
- Ingestion points: PR and issue comments are fetched via the
gh apicommand as defined inSKILL.md. - Boundary markers: No explicit markers or instructions to ignore embedded prompts are provided to isolate the fetched external content.
- Capability inventory: The agent can execute
ghCLI commands and potentially perform further actions based on the interpretation of fetched comments. - Sanitization: Fetched comment text and code diffs are passed directly to the output format without validation, escaping, or filtering of the content.
Audit Metadata