slop-fix-repo-issues
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an entry point for processing GitHub issues, which are untrusted external data sources that may contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Untrusted data enters the context when the skill searches for and fetches issue details using the
ghCLI (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the content of the issues being processed.
- Capability inventory: While this coordinator skill has limited direct capabilities, it delegates to
$slop-fix-issueand$create-pr, which are capable of modifying source code and creating pull requests. - Sanitization: There is no mention of sanitizing or validating the issue content (e.g., stripping markdown comments or HTML) before it is passed to the sub-skills for implementation.
Audit Metadata