agents-sdk

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and prefer retrieval from the public GitHub docs at https://github.com/cloudflare/agents/tree/main/docs, which are open/public third-party content that the agent is required to read and that can materially influence its implementation and tool use, creating a clear avenue for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to "Fetch current docs from https://github.com/cloudflare/agents/tree/main/docs before implementing," meaning that at runtime it will retrieve that external GitHub content which directly controls implementation prompts/instructions and is treated as a required dependency.