yds-gh-issue-drafter
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform repository operations including viewing repository metadata, listing/creating labels, and creating issues. These commands are necessary for the skill's primary function and are performed locally using the user's authenticated environment. - [INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary user input (rough intent) to populate GitHub issue content. While this presents an ingestion surface for potentially malicious text, the skill effectively mitigates this risk by requiring the user to review and approve the final draft in Step 4 before the
gh issue createcommand is executed. - Ingestion points: User input captured during intent capture (SKILL.md Step 1).
- Boundary markers: Explicit manual confirmation step required before any side effects (Step 4).
- Capability inventory: Execution of shell-based CLI tools (
gh,jq) via subprocess. - Sanitization: Relies on human verification of the interpolated content prior to execution.
- [SAFE]: The skill follows security best practices for AI agents by ensuring no side effects occur without user consent and by using standard, well-known utilities for its operations.
Audit Metadata