test-driven-development

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill utilizes authoritative language and strict behavioral constraints (e.g., "The Iron Law," "No exceptions," and "Delete means delete") to override default agent behavior and enforce a rigid methodology.
  • [COMMAND_EXECUTION]: Instructions direct the agent to perform shell executions, specifically npm test, to validate test results during the lifecycle of a feature or bugfix.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes user-provided source code and test definitions without adequate protection. \n
  • Ingestion points: The agent is instructed to read and analyze user-provided source code and TypeScript files (e.g., path/to/test.test.ts). \n
  • Boundary markers: No delimiters or "ignore embedded instructions" warnings are specified for the external content being processed. \n
  • Capability inventory: The skill utilizes shell command execution via npm test and commands the agent to perform destructive file system modifications (directives to "Delete it" in SKILL.md). \n
  • Sanitization: No sanitization, validation, or escaping of the user-provided content is performed before the agent acts upon it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:35 PM