user-story-delivery
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub issues, comments, and repository instructions, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The workflow (Step 1) requires reading repository instructions, GitHub issues, comments, and linked work items.
- Boundary markers: There are no explicit instructions or delimiters defined to separate user-provided instructions from external data or to warn the agent against executing instructions found in issue comments.
- Capability inventory: The skill coordinates delegated workers for implementation and review. These workers likely have the capability to write files, execute commands (for verification), and perform network operations (interacting with the GitHub API).
- Sanitization: The skill does not specify any sanitization, filtering, or validation of the content retrieved from external GitHub sources before processing.
Audit Metadata