The Agent Skills Directory

[SAFE]: The skill implements a standard development workflow (implementation, testing, and checklist verification). No malicious patterns such as data exfiltration, command injection, or obfuscation were detected.
[COMMAND_EXECUTION]: The skill provides example commands for running tests (e.g., ./gradlew test, npm test) and linting. These are routine development activities within the context of a code development skill and do not present a security risk.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns or unverified dependencies were found.
[INDIRECT_PROMPT_INJECTION]: The skill reads from local documents (design, tasks, and testing docs). While this constitutes an attack surface, the risk is minimized as these documents are part of the internal project iteration and are not sourced from untrusted external entities.

code-development