gh-issue-planner
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill fetches issue data (title, body, comments) from GitHub using the official
ghCLI. While this external data could theoretically contain malicious instructions (Indirect Prompt Injection), the workflow includes a mandatory user confirmation step (Step 5) before any write actions are performed. - [SAFE]: Command execution is restricted to standard repository investigation tools and the GitHub CLI. No unauthorized network access or external script downloads were detected.
- [SAFE]: The shell command for posting comments uses a quoted heredoc (
<<'EOF'), which is a security best practice to prevent the shell from interpreting or executing any code that might be contained within the generated response plan.
Audit Metadata