graphify

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

• Third-party content exposure detected (low risk: 0.10). The workflow processes local files and user-specified URLs (/graphify add <url>), which constitutes low-risk active fetching of external content rather than automatic ingestion from a monitored outsider-authored feed.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references a GitHub repository URL for documentation and uses pip to install an unofficial package graphifyy, which lacks strong first-party provenance or verifiable repository roots.