mastra

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 fetch remote documentation from https://mastra.ai/llms.txt and related markdown files using WebFetch, exposing the agent to arbitrary web-fetched content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references remote documentation endpoints (mastra.ai/llms.txt) for runtime retrieval and behavior guidance without strong first-party verification of the fetched content's integrity or immutable provenance, qualifying as a medium-risk unofficial operational dependency.