wechat-article-formatter

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a Python script (scripts/markdown_to_html.py) and standard Unix utilities like ls, grep, and head for file discovery and quality verification.- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it processes untrusted data from external Markdown files.
  • Ingestion points: Untrusted content enters the agent's context through user-provided Markdown files or content pasted into the environment.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' warnings when the agent reads or processes the file content.
  • Capability inventory: The skill has access to Bash (shell execution), Read (file access), and Write (file modification), which are utilized in the formatting workflow.
  • Sanitization: Absent; there is no instruction to validate, escape, or sanitize the input content before it is passed to the shell commands or the conversion script.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 06:11 AM