tdd
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read files from the user's codebase, such as
GLOSSARY.mdand Architecture Decision Records (ADRs), to align its testing strategy with the project's domain language. This creates an attack surface where malicious instructions embedded in these files could influence agent behavior. - Ingestion points:
GLOSSARY.mdand Architecture Decision Records (ADRs) found in the user's repository. - Boundary markers: The instructions do not provide explicit delimiters or warnings for the agent to disregard potential instructions within these files.
- Capability inventory: While following this skill, an agent typically has file system access and terminal execution capabilities to perform TDD tasks.
- Sanitization: The skill does not mention any sanitization or filtering of the content read from these external files.
- [EXTERNAL_DOWNLOADS]: The skill contains references to an external GitHub repository (
github.com/mattpocock/skills) within its provenance and upstream configuration files. These are used neutrally for attribution, version tracking, and integrity verification.
Audit Metadata