The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to override agent behavior, bypass safety filters, or extract system prompts were detected.
[Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local file paths (such as SSH keys or AWS credentials) and performs no network operations.
[Obfuscation] (SAFE): All skill components are provided in clear text without any Base64, zero-width characters, or other encoding techniques.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download external packages or execute remote scripts. It operates entirely on the local project structure.
[Command Execution] (SAFE): The script scripts/detect_test_env.sh performs read-only introspection of the project environment using standard utilities like find and grep. It does not require elevated privileges or execute untrusted input.
[Indirect Prompt Injection] (SAFE): While the skill reads project configuration files (e.g., package.json, pyproject.toml), the processing is limited to static string matching for framework detection, which does not facilitate instruction injection.

tdd-workflow