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
Risk Level
SAFE
Analyzed
Aug 26, 2026, 08:53 PM
Security Audit — agent-trust-hub — issues