agent-sdk-builder

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and analyze external documentation and code from public third-party URLs (https://docs.openhands.dev/llms.txt and the GitHub repos at https://github.com/OpenHands/software-agent-sdk and https://github.com/OpenHands/docs), which the agent must read and use to drive implementation decisions.

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 at runtime to fetch and clone external resources (https://docs.openhands.dev/llms.txt, https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk, https://github.com/OpenHands/docs/tree/main/sdk), and those fetched documents/repos are required and used to shape the agent's prompts/instructions and implementation plan, creating a high-confidence runtime dependency on external content.