The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the mineru-open-api command-line tool via npm or from the official OpenDataLab GitHub repository. These are verified vendor resources used for the skill's primary functionality.
[DATA_EXFILTRATION]: Document content and web page data are transmitted to the MinerU API (mineru.net) for server-side extraction. This behavior is clearly documented in the skill's privacy metadata and is the intended operation of the service.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute mineru-open-api commands. The execution is restricted to the specific CLI binary via platform configuration.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documents and web content which could potentially contain embedded instructions. This is an inherent risk for document parsing tools.
Ingestion points: Processes local files and remote URLs through the extract, flash-extract, and crawl commands in SKILL.md.
Boundary markers: No explicit instruction delimiters or 'ignore embedded content' warnings are present in the provided prompts.
Capability inventory: The agent can execute the CLI tool and perform file operations via Bash.
Sanitization: Input documents are processed by the external API; no client-side sanitization of the extracted text is defined within the skill itself.

MinerU Document Extractor