agentation

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

• Third-party content exposure detected (high risk: 0.90). The skill configures an Agentation MCP server to sync user-created annotations into Claude (see steps 7–8 and the note "annotations will now sync to Claude automatically" in SKILL.md), which exposes the agent to untrusted, user-generated third-party content that could contain instructions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes npx agentation-mcp (which fetches and executes remote code from the npm registry, e.g. https://registry.npmjs.org/agentation-mcp or https://www.npmjs.com/package/agentation-mcp) as a required runtime step to run an MCP server that can execute code and influence agent behavior, so this is a runtime external dependency that executes remote code.