getting-started

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly directs the agent to fetch the public docs map at https://docs.opensaas.sh/llms.txt and then retrieve the "Getting Started" guide from a raw.githubusercontent.com URL and use it as the source of truth for installation and runtime actions, which clearly exposes the agent to untrusted third-party content that could contain injected instructions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill fetches runtime instructions from https://docs.opensaas.sh/llms.txt and then loads the referenced raw.githubusercontent.com "Getting Started" guide to use as the source-of-truth for its prompts and actions, so external content directly controls agent instructions at runtime.