skills/zju-real/easel/doc-convert/Gen Agent Trust Hub

doc-convert

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided Markdown content, which represents an untrusted data ingestion surface.
  • Ingestion points: The doc_convert.py script takes an input file (e.g., article.md) provided by the user.
  • Boundary markers: There are no instructions for the agent to use specific delimiters or to ignore potential instructions embedded within the Markdown text.
  • Capability inventory: The skill has the capability to execute Python scripts and write output files to the outputs/ directory.
  • Sanitization: The instructions do not define any sanitization or validation steps for the input Markdown before rendering it via Chromium.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the markdown and playwright packages, as well as the Chromium browser engine via playwright install chromium. These are well-known, industry-standard tools for document processing and web automation.
  • [COMMAND_EXECUTION]: The skill relies on executing a local Python script skills/shared/scripts/doc_convert.py to perform the document conversion tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 01:21 PM