edge-find-skills

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and loads third-party public agent skills via Edge from getedge.cc, allowing authors of those public skills to supply untrusted reference instructions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to dynamically connect to and load instructions from a remote MCP server via getedge.cc, which constitutes a weak external operational dependency.