fetch-pr-comments
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a bash script (
scripts/fetch-pr-data.sh) that executes thegh(GitHub CLI) andjqcommands to query the GitHub GraphQL API and process the results. - [EXTERNAL_DOWNLOADS]: The bash script performs network requests to GitHub's official API to retrieve pull request data. GitHub is a well-known service and the data retrieval is necessary for the skill's functionality.
- [PROMPT_INJECTION]: The skill ingests untrusted data in the form of GitHub pull request comments and review bodies, which creates a surface for indirect prompt injection.
- Ingestion points: The
bodyfields of reviews and comments fetched from GitHub by thescripts/fetch-pr-data.shscript. - Boundary markers: The skill instructions specify that the agent should display the comment bodies using blockquote formatting (
>). - Capability inventory: The agent has capabilities for shell command execution and file system access.
- Sanitization: No sanitization, escaping, or instruction-filtering is applied to the comment bodies before they are presented to the agent.
Audit Metadata