ghwf4-review
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) and Git to perform operations. It specifically executes commands to view issue/PR data and automate thegit add,commit, andpushworkflow for documentation updates. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from GitHub issue bodies, PR descriptions, and comments.
- Ingestion points: Data enters the context via
gh issue viewandgh pr viewin Step 1 of the processing logic. - Boundary markers: The instructions do not define delimiters or specific warnings to the agent to ignore instructions embedded within the fetched GitHub content.
- Capability inventory: The skill has the ability to execute shell commands (
gh,git), read/write local files (state.json, review documents), and push changes to remote repositories. - Sanitization: There is no evidence of sanitization, filtering, or validation of the text retrieved from GitHub before it is used by the agent to generate the review document.
Audit Metadata