create-compelling-issues
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for creating high-quality GitHub issues, including searching for duplicates and verifying repository policies. It uses standard tools like the GitHub CLI (gh) for information retrieval.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content from GitHub search results and repository playbooks. While this presents an attack surface where malicious text in an issue could attempt to influence the agent, the skill's instructions focus on information gathering and documentation rather than executing content found in those sources. Evidence chain: 1. Ingestion points: gh search results and repository configuration files (playbooks). 2. Boundary markers: No explicit delimiters are mandated for external content. 3. Capability inventory: Access to Bash, Write, and Read tools. 4. Sanitization: No explicit sanitization of retrieved issue content is described.
Audit Metadata