graphify

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

• Third-party content exposure detected (low risk: 0.10). The skill manages a local knowledge graph CLI tool and defines an ingestion command (graphify add <url>) that fetches external URLs into local directories, but it does not run an automated monitoring loop or continuous ingestion queue that exposes the agent to outsider-authored free text without user selection.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external GitHub repository (https://github.com/akillness/jeo-skills) via npx skills add to install skill material during setup, but the source has unknown provenance and unofficial publisher status, making it a weak external operational dependency.