speech-pathology-ai

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

• Third-party content exposure detected (low risk: 0.10). The skill uses the Firecrawl search tool to fetch web content on demand, representing 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 references external Python package repositories and pretrained model hubs (facebook/wav2vec2-xls-r-300m, vitouphy/wav2vec2-xls-r-300m-timit-phoneme) via Hugging Face during setup and runtime instructions, which qualify as weak/unknown/suspicious operational dependencies due to lack of enforced cryptographic provenance.