matt-tdd
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and best practices for TDD and integration testing. All instructions and examples are consistent with standard software development practices.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions tell the agent to run 'tw brief' and 'tw read' to ingest project-specific knowledge. This represents an attack surface for indirect prompt injection if the ingested project files are maliciously crafted, though it is a standard feature for development agents. 1. Ingestion points: Project documentation, glossary, and rules accessed via the 'tw' tool in SKILL.md. 2. Boundary markers: No explicit instructions for delimiters or untrusted data handling are provided. 3. Capability inventory: The skill implies the agent has capabilities for feature development, bug fixing, and test execution. 4. Sanitization: No sanitization of ingested content is specified.
Audit Metadata