gh-issue-drafter

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the official GitHub CLI (gh) and jq for repo metadata, label management, and issue creation. These actions are appropriate for its task.
  • [PROMPT_INJECTION]: The skill manages the risk of indirect prompt injection by requiring explicit human approval before creating issues. It uses structured headers (Done, Out of Scope) as boundary markers and employs shell here-docs (cat <<'EOF') to ensure user-provided content is treated as data rather than executable code during the creation process.
  • [DATA_EXPOSURE]: No sensitive files or credentials are accessed. The skill only retrieves non-sensitive repository information via standard gh commands.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute any external scripts or unverifiable packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 02:33 PM
Security Audit — agent-trust-hub — gh-issue-drafter