Doc To Text
Analysis
This skill is purpose-aligned for converting Word documents to readable text, but users should trust the MinerU CLI/provider and protect any MinerU token and private documents.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
npm install -g mineru-open-api # or via Go (macOS/Linux): go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
The skill depends on installing an external global CLI package, and the Go command tracks the latest version rather than a pinned release. This is central to the skill, but users should trust the package source.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Token required for `.doc` and `extract`: mineru-open-api auth # Interactive token setup export MINERU_TOKEN="your-token"
The skill requires a MinerU token for some modes. This is expected for a MinerU API-based extraction workflow, but it is still account credential material.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Supported input: .doc, .docx (local file or URL) ... Token required for `.doc` and `extract`
The skill processes local files or URLs through the MinerU CLI/API flow, with token-backed extraction for some modes. The artifacts do not provide detailed privacy or retention boundaries for document content.
