infrastructure-engineer

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md contains an explicit required directive to "Read https://wazoo.dev's JSON-LD graph" to synchronize company details, which instructs the agent to fetch and interpret open/public third-party content that can influence its behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent at runtime to "Read https://wazoo.dev's JSON-LD graph to synchronize with the company," which requires fetching external content that will directly alter the agent's prompts/knowledge and thus controls its behavior.