tdd-plan

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a multi-step chain where its output markdown plans serve as instructions for downstream skills like red-green-refactor.
  • Ingestion points: The skill ingests untrusted user requests for new features, products, or bugfixes as defined in the SKILL.md procedure.
  • Boundary markers: The skill structures user input into predefined markdown templates provided in assets/plan-template.md to delineate user-provided goals from instructions, though no explicit negative constraints or safety delimiters are specified for the input data.
  • Capability inventory: The skill's primary capability is writing structured markdown files and directories to the plans/ folder based on the user request.
  • Sanitization: The skill processes the input by restating the feature outcome and decomposing it into vertical slices, which acts as a manual review and restructuring of the original input before it is written to the execution plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 11:53 AM
Security Audit — agent-trust-hub — tdd-plan