The Agent Skills Directory

[SAFE]: No malicious patterns such as prompt injection, obfuscation, or data exfiltration were detected. The skill focuses on established software engineering practices.
[COMMAND_EXECUTION]: The skill suggests the use of standard development tools and test runners, including node --test, npx vitest, npx jest, pytest, go test, and cargo test. These are used appropriately for their intended purpose of executing local test suites.
[DYNAMIC_EXECUTION]: The skill involves the creation and execution of code generated by the agent as part of the TDD loop. This is the primary function of the skill and does not involve the execution of untrusted remote code.
[INDIRECT_PROMPT_INJECTION]: While the skill interacts with project configuration files (e.g., package.json, pyproject.toml) and user-provided requirements, it does so within a controlled development workflow. No exploitable surfaces for instruction hijacking were identified.

tdd