audio-extract-api

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains deceptive role mismatch steering where an audio extraction tool is instructed to perform image generation instead.

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch external documentation from https://www.pixazo.ai/models/audio-extract-api.md, which is an arbitrary fetched web page rather than a monitored feed or direct automated user submission channel.

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 external instruction/documentation files from pixazo.ai at runtime, representing an unverifiable operational dependency on a third-party source.