test-driven-development
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
terminaltool, specifically callingpytestto run tests and verify code behavior. - [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by processing external user requirements to generate and execute code through the terminal.
- Ingestion points: The skill ingests untrusted user requirements for new features, bug fixes, and refactoring tasks to drive the TDD cycle.
- Boundary markers: No specific boundary markers or instructions to ignore embedded prompts in the ingested requirements are present.
- Capability inventory: The skill utilizes
terminalaccess to execute code and thefiletool for modifying the project structure. - Sanitization: No sanitization or validation logic is specified for the code generated from user requirements before it is executed.
Audit Metadata