content-parser

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

• Third-party content exposure detected (low risk: 0.10). The skill extracts content from arbitrary URLs provided by the user, which can contain outsider-authored free text retrieved via web page extraction or search results.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes API calls to an external third-party service (Marswave/ListenHub) for content extraction, which represents an operational runtime dependency with common/reputable unofficial provenance.