wechat-article-formatter

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill utilizes local Python scripts and Bash commands (ls, head, grep) to manage file conversion and verification, which is standard for its intended use case.
  • [EXTERNAL_DOWNLOADS] (SAFE): Dependencies listed in requirements.txt are well-known, reputable Python libraries from standard repositories.
  • [PROMPT_INJECTION] (LOW): Identified a surface for indirect prompt injection (Category 8) due to its data processing workflow.
  • Ingestion points: Processes user-provided Markdown files (SKILL.md, Step 1) and generated HTML output (Step 3).
  • Boundary markers: Absent; the system instructions do not include delimiters or warnings to disregard potential instructions within the processed text.
  • Capability inventory: The skill uses Bash, Read, and Write tools to execute logic and inspect file contents.
  • Sanitization: No specific sanitization or filtering of input Markdown content is performed before processing or inspection.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:41 PM