skills/openclaw/skills/mineru/Gen Agent Trust Hub

mineru

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines workflows using local shell commands including mkdir, cd, jq, and unzip to handle directory structures and process API responses.
  • [EXTERNAL_DOWNLOADS]: The skill fetches document parsing results from mineru.net, which is the official domain for the MinerU service.
  • [PROMPT_INJECTION]: The skill presents a potential surface for indirect prompt injection as it processes untrusted external content. 1. Ingestion points: File URLs provided to the /api/v4/extract/task endpoint in SKILL.md. 2. Boundary markers: None identified in the provided instructions. 3. Capability inventory: Includes shell commands for file manipulation and unzipping archives in SKILL.md. 4. Sanitization: No evidence of input sanitization or validation of the parsed output is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 03:49 AM