pick-next-issue
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches issue content and comments from GitHub using the
ghCLI, which serves as an entry point for untrusted external data. - Ingestion points: The
gh issue listandgh issue viewcommands in Step 1 and Step 4 retrieve titles, bodies, and comments from a remote repository. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the issue content.
- Capability inventory: The skill chains with the
/turboplanskill in Step 5, passing the potentially untrusted issue body as a task description. Depending on the capabilities of/turboplan, this could lead to the execution of malicious instructions included in an issue. - Sanitization: No sanitization, escaping, or filtering of the fetched GitHub data is performed before it is passed to the next skill.
Audit Metadata