visual-review
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to view pull request metadata and fetch diffs. These are standard operations for a development-focused skill and use legitimate tooling. - [REMOTE_CODE_EXECUTION]: No remote code execution was detected. The skill generates a local HTML file and opens it using the system's default browser tool (
openorxdg-open). - [DATA_EXFILTRATION]: No evidence of data exfiltration. The skill reads local PR data and generates a local HTML report. It explicitly notes that it is 'read-only' and does not post data back to GitHub or external servers.
- [PROMPT_INJECTION]: No prompt injection or bypass attempts were found. The instructions are focused on the task of code review and report generation.
- [OBFUSCATION]: No obfuscated code, hidden URLs, or encoded payloads were detected in the skill files.
Audit Metadata