operations-manager

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's On load instruction explicitly tells the agent to "Read https://wazoo.dev's JSON-LD graph" (in SKILL.md), which requires fetching and ingesting public third-party content that the agent will interpret to synchronize company state and thus can influence its decisions.

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 runtime to "Read https://wazoo.dev's JSON-LD graph to synchronize with the company," meaning it fetches remote content that will directly influence agent behavior and prompts, creating a high-confidence runtime dependency on that external URL.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 11:52 PM