fetch-pr-comments
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub PR comments and reviews, which creates a potential surface for indirect prompt injection.\n
- Ingestion points: The skill fetches PR titles, review bodies, and comment bodies from GitHub using the
scripts/fetch-pr-data.shscript.\n - Boundary markers: The instructions direct the agent to wrap comment bodies in blockquotes (
>) and diff hunks in fenced code blocks, providing clear separation between external data and agent instructions.\n - Capability inventory: The skill uses the GitHub CLI to read data and executes a local bash script. It does not have file-write or general network capabilities beyond the GitHub API calls.\n
- Sanitization: No explicit sanitization or filtering is performed on the fetched content before presentation to the agent.\n- [COMMAND_EXECUTION]: The skill executes a local bash script
scripts/fetch-pr-data.shto fetch data via the GitHub CLI. This is the intended primary function of the skill and uses standard system tools (bash,gh,jq) correctly.
Audit Metadata