data-scientist
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs (in SKILL.md under "Fetch company details") the agent to read https://wazoo.dev's JSON-LD graph, which is a public third-party URL whose content the agent must ingest and could therefore influence its behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs at load time to fetch https://wazoo.dev's JSON-LD JSON-LD graph to "synchronize with the company", which is a required runtime fetch whose content would directly control agent prompts/instructions.
Audit Metadata