Skills
skills/staruhub/claudeskills/Geek-skills-mineru-pdf-parser/Gen Agent Trust Hub

Geek-skills-mineru-pdf-parser

Warn

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/mineru_parse.py utilizes the os.system() function to perform environment setup tasks, such as installing dependencies and downloading required models.\n
  • Evidence: Found os.system("pip install uv && uv pip install -U 'mineru[all]'") and os.system("mineru-models-download") within the install_mineru function in scripts/mineru_parse.py.\n- [EXTERNAL_DOWNLOADS]: The skill triggers the download of the mineru package and associated large language models from public registries.\n
  • Evidence: Instructions in SKILL.md and automated calls in scripts/mineru_parse.py initiate downloads from PyPI and model hosting platforms.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it extracts text from untrusted PDF files which may contain adversarial instructions.\n
  • Ingestion points: External PDF data is processed via mineru.parse(input_path) in scripts/mineru_parse.py.\n
  • Boundary markers: The skill lacks delimiters or explicit warnings to the agent to treat the extracted content as untrusted data.\n
  • Capability inventory: The script possesses capabilities for shell command execution (os.system) and file system manipulation.\n
  • Sanitization: There is no evidence of sanitization or filtering of the content extracted from PDF documents before output.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 26, 2026, 03:10 AM