tdd-pstack
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze user-provided bug descriptions to create regression tests. This creates a surface for indirect prompt injection if a bug report contains adversarial instructions meant to influence the agent. However, this is inherent to coding tasks and the instructions do not encourage unsafe handling.\n
- Ingestion points:
SKILL.mdworkflow begins by understanding user-provided bug reports and observable reproductions.\n - Boundary markers: The instructions do not define specific delimiters for separating user bug data from the agent's internal instructions.\n
- Capability inventory: The agent is expected to have tool access for writing files and executing shell commands to run tests.\n
- Sanitization: No specific input sanitization steps are defined, which is typical for instructions focused on development workflows.\n- [DYNAMIC_EXECUTION]: The core TDD workflow involves the dynamic creation and execution of new test scripts (unit, component, or integration tests) at runtime. This is the intended primary purpose of the skill and follows standard development practices.
Audit Metadata