product-manager

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "Read https://wazoo.dev's JSON-LD graph to synchronize with the company," which requires fetching and interpreting content from a public website and could materially influence the agent's decisions or actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs an on-load runtime fetch of https://wazoo.dev to read its JSON-LD graph and "synchronize" company details, which means remote content would be injected into the agent's context and could directly influence prompts/instructions, and is a required dependency.