builder-role-skill
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external files that could contain instructions intended to override agent behavior. \n
- Ingestion points: The skill (Workflow Step 1.1) reads external files including DEVELOPMENT_PLAN.md, ARCHITECTURE.md, TODO.md, and MULTI_AGENT_PLAN.md. \n
- Boundary markers: Absent. No instructions are provided to the agent to treat the content of these external files as data only or to ignore embedded commands. \n
- Capability inventory: The skill utilizes shell-based tools including npm (testing and linting), git (version control), and gh (GitHub CLI for pull requests). \n
- Sanitization: Absent. There are no mechanisms described for validating or sanitizing the content ingested from the external planning documents.
Audit Metadata