communications-specialist
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: 0.90). The skill explicitly instructs the agent to "Read https://wazoo.dev's JSON-LD graph" on load, meaning it fetches and ingests content from a public website that the agent will parse and use to drive messaging and actions, exposing it to untrusted third-party content that could alter 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 on-load to fetch and "Read https://wazoo.dev's JSON-LD graph to synchronize with the company," a runtime retrieval of external structured data that would be injected into the agent context and can directly shape prompts/instructions.
Audit Metadata