The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions designed to override agent behavior, bypass safety guidelines, or extract system prompts were detected.
[Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials (API keys, tokens), or unauthorized network operations were found.
[Obfuscation] (SAFE): All content is in clear text. There are no signs of Base64 encoding, zero-width characters, or homoglyph attacks.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill references standard testing frameworks (Jest, Pytest). It mentions common development commands like npm run test and pytest -q but does not download or execute untrusted remote scripts.
[Privilege Escalation & Persistence] (SAFE): There are no commands attempting to gain administrative privileges (e.g., sudo) or establish persistence on the host system.
[Indirect Prompt Injection] (LOW): The skill acts as a code generator which ingests user-provided source code. While this is a known attack surface, the risk is categorized as LOW because the skill provides structured templates and doesn't possess capabilities that could be easily weaponized via the generated test code.

test-generator