sdlc
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and logic-based, designed to recommend specific workflows to the agent. It does not perform any file system modifications, network requests, or shell command executions.
- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data, as it is instructed to inspect external contexts like Jira tickets, PRDs, and repository artifacts. However, the risk is negligible because the skill's capabilities are restricted to generating textual reports and recommendations. No boundary markers or input sanitization mechanisms are defined in the instructions for these ingestion points.
Audit Metadata