audio-denoise-api

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches documentation from a URL specified in the skill, which constitutes low-risk dynamic content fetching.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch a remote Markdown file from an external domain (https://www.pixazo.ai/models/audio-denoise-api.md) at runtime for behavior-selecting configuration/instructions, constituting a weak/unknown external operational dependency.