wechat-article-formatter

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the lack of isolation for external data.
  • Ingestion points: Processes untrusted content from Markdown files and local image directories.
  • Boundary markers: The workflow does not include delimiters or instructions to ignore embedded commands within the processed Markdown.
  • Capability inventory: The skill utilizes Bash, Read, Write, Edit, Glob, and Grep, granting it significant file system and command execution permissions.
  • Sanitization: There is no explicit process for validating or escaping the input Markdown content before it is read into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 11:39 AM