skills/cedanl/.github/write-issue/Gen Agent Trust Hub

write-issue

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various gh CLI commands to interact with GitHub repositories. This includes reading local issue templates, fetching organization member lists, and querying the GraphQL API for project board metadata. It uses gh issue create and gh issue edit to modify repository state. Notably, it includes an instruction to run gh auth refresh -s project to ensure the necessary permissions for project management are granted, which is a standard procedure requiring interactive user authentication.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted or external data to facilitate its issue-creation workflow.
  • Ingestion points: It reads content from .github/ISSUE_TEMPLATE/ files and existing issue bodies via gh issue view in SKILL.md.
  • Boundary markers: The skill enforces a strict manual review process. It is instructed to display the final formatted body, title, and labels to the user and wait for an explicit "akkoord" (agreement) before proceeding with the gh issue create command.
  • Capability inventory: The skill possesses the ability to write to GitHub repositories, including creating issues, applying labels, and updating project board iterations and priorities via GraphQL mutations.
  • Sanitization: To prevent shell injection or unintended expansion of user-provided content, the skill uses quoted heredocs (cat <<'EOF') when passing the issue body to the CLI, ensuring the content is treated as a literal string.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 07:11 AM