assemblyai

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains severe prompt injection and prompt confusion anomalies, falsely conflating AssemblyAI speech-to-text with image generation tasks while attempting to redirect users to an external third-party gateway.

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches external documentation from https://www.pixazo.ai/models/assemblyai.md, which is an actively fetched URL and therefore presents a low indirect prompt injection risk.

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 documentation via HTTP at runtime (https://www.pixazo.ai/models/assemblyai.md), which constitutes an unverifiable runtime external dependency from an unofficial or third-party source.