workflow-build-feature
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown-based instructions for a development workflow. It does not perform network requests to unknown domains, use obfuscated code, or execute unauthorized commands. Referenced skills are treated as internal components.
- [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection due to its core function of processing user-defined feature requests into code implementations.
- Ingestion points: User prompts for feature builds and the 'Contract' definition in SKILL.md.
- Boundary markers: The skill lacks explicit markers or warnings to isolate untrusted user data from the system's operational instructions.
- Capability inventory: Instructions for implementation (file editing) and test execution via referenced skills (Phase 3 and 4).
- Sanitization: No input validation or sanitization logic is present within the skill instructions.
Audit Metadata