The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run the npm test command to verify code behavior during the TDD cycle. This is a standard and expected operation for development workflows.- [PROMPT_INJECTION]: The instructions use strong, imperative language (e.g., "The Iron Law", "Delete means delete") to maintain adherence to the TDD methodology. These function as behavioral constraints for the task and do not attempt to bypass core safety guardrails or extract system prompts.- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it processes external codebase data (Ingestion points: project source code and test results). The agent has the capability to write to local files and execute shell commands like npm test (Capability inventory: file writing, command execution). The instructions do not define specific boundary markers or sanitization logic for the handled data (Boundary markers: absent; Sanitization: absent), which is typical for development-oriented skills.- [SAFE]: No evidence of obfuscation, data exfiltration, hardcoded credentials, or unauthorized remote code execution was found across the analyzed files.

test-driven-development