connect-tool

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly instructs the agent that if the user pastes an API key in the chat, it should pipe it into a python command (printf '%s' '<key>' | python3 ...), which involves handling the raw secret value within the chat context and output stream.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required workflow involves connecting tools and fetching API data or documentation from user-selected services, constituting an active search/fetch of external content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading code and instruction files from an arbitrary GitHub repository at runtime (https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/...), presenting a weak/unknown provenance operational dependency.