chainstack

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to search documentation and fetch doc pages, which is active user-guided fetching of documentation pages, presenting a low indirect prompt injection risk.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to fetch and update its instructions from https://mcp.chainstack.com/skill if tools fail, constituting a runtime external dependency that controls agent instructions.