tdd-implement
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a structured and transparent development workflow with clear separation of duties and includes security scanning (gosec, govulncheck) as a mandatory part of the implementation cycle.
- [COMMAND_EXECUTION]: The coordination agent executes standard Go development and security tools including gofmt, go vet, go test, govulncheck, and gosec to verify the quality and security of the implemented code.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by reading project specification files and user arguments which are then interpolated into sub-agent prompts. 1. Ingestion points: $ARGUMENTS in SKILL.md and project files such as .specify/memory/serena/index.md and CLAUDE.md. 2. Boundary markers: Absent; instructions do not specify the use of delimiters when interpolating requirements into sub-agent prompts. 3. Capability inventory: Local command execution for Go tooling and multi-agent team management (TeamCreate, SendMessage). 4. Sanitization: Absent; the skill trusts the content of local project specification files as context for code generation.
Audit Metadata