creator

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

• Third-party content exposure detected (low risk: 0.10). The workflow consumes URL input from the user and extracts content via an external API (Marswave openapi), which handles outsider-authored web content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill uses external API URLs (https://api.marswave.ai/openapi/v1/content/extract) at runtime to fetch and parse external content that is then injected into the model context to control agent tasks.