mineru-parser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to ask the user for their API token (if not in env) and then embed that token into Authorization headers/requests (e.g., f"Bearer {token}"), which requires the LLM to handle and output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 1 "Submit parsing task" with the "url" parameter and Step 3 "Retrieve Results") instructs the agent to fetch and download arbitrary file URLs and then extract/interpret the returned markdown/JSON from those public files, which are untrusted third‑party content that could contain instructions influencing agent behavior.