whisper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains deceptive capability misdirection, describing an audio transcription service while actually performing image generation and executing unauthorized API calls.

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

• Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to fetch documentation from an external URL (https://www.pixazo.ai/models/whisper.md), exposing it to low-risk indirect prompt injection from web content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch external documentation (https://www.pixazo.ai/models/whisper.md) to govern its behavior and parameters, constituting an unverified runtime external dependency from an unofficial third-party source.