wechat-content-optimizer

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a workflow step that executes a local Node.js script using a shell command template. This template includes a placeholder for a user-provided file path. If the agent does not properly sanitize or escape this input, an attacker could potentially execute arbitrary shell commands by providing a path containing shell metacharacters.
  • [PROMPT_INJECTION]: The skill processes untrusted data from local Markdown files, creating an attack surface for indirect prompt injection. Malicious instructions embedded within a file could attempt to override the agent's optimization logic or extract sensitive information.
  • Ingestion points: The script scripts/optimize.js reads the entire content of a user-specified Markdown file and outputs it to the agent.
  • Boundary markers: The script utilizes ---FILE_CONTENT_START--- and ---FILE_CONTENT_END--- as delimiters to demarcate the untrusted content.
  • Capability inventory: The agent has the capability to read local files, execute a provided Node.js script, and write optimized content (potentially overwriting original files) to the filesystem.
  • Sanitization: No sanitization, instruction filtering, or safety validation is performed on the content of the Markdown file before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:14 PM