tdd

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources such as task cards, issue descriptions, and project-specific documentation.
  • Ingestion points: The skill reads project files including docs/coding-standard/, docs/code-review-checklist/, CLAUDE.md, AGENTS.md, and existing test files. It also derives behavior lists from external task/issue descriptions.
  • Boundary markers: The instructions do not specify the use of boundary markers or delimiters when interpolating external file content into the agent's context.
  • Capability inventory: The skill performs shell-based operations, including running test suites, linters, formatters, and type-checkers (Run the project's full gate).
  • Sanitization: There is no evidence of sanitization or validation for the content retrieved from project files or task descriptions before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 07:58 AM