issues
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill leverages the
gh(GitHub CLI) tool within a Bash environment to perform actions such as creating, viewing, and listing issues. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted user input into shell command arguments, creating a surface for indirect prompt injection. 1. Ingestion points: User-provided titles, bodies, and labels captured via the AskUserQuestion tool in SKILL.md. 2. Boundary markers: The instructions recommend using shell HEREDOC syntax (
cat <<'EOF') for the issue body, which provides a structural boundary. 3. Capability inventory: Shell execution capabilities via the Bash tool to run GitHub CLI commands. 4. Sanitization: The skill utilizes HEREDOCs to handle body content formatting and mitigate basic command injection, although other fields such as titles use standard quote interpolation.
Audit Metadata