tdd
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by accepting arbitrary feature requirements without sanitization or boundary markers.
- Ingestion points: The argument in SKILL.md receives untrusted data from the user.
- Boundary markers: There are no delimiters around the requirement input to prevent the agent from obeying instructions embedded within it.
- Capability inventory: The skill uses tools such as Write, Edit, and Bash to modify files and execute commands.
- Sanitization: No validation or sanitization logic is present to filter malicious content from the user-provided requirements.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run test suites.
- Evidence: Includes npm test in SKILL.md and others like pytest, go test, and cargo test in examples/multi-ecosystem.md. These are necessary for the TDD workflow but represent an execution surface for code written by the agent.
Audit Metadata