llamaparse-mcp

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md instructs the agent to fetch files from arbitrary public URLs using "uploadFileByUrl" and to parse/extract that content with "parseFile" (often passing markdown to an LLM), meaning untrusted third‑party content from the open web can be ingested and influence downstream parsing, classification, and actions.