baoyu-cover-image

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): No malicious patterns or security vulnerabilities were detected.
  • File Operations: The skill uses basic shell commands like test -f to manage its own configuration file (EXTEND.md) and directory structures. These operations are restricted to the skill's local storage or project-specific paths.
  • Indirect Prompt Injection (SAFE): The skill ingests untrusted article content to generate prompts for an image generator. This surface is managed by using structured prompt templates (found in references/base-prompt.md) and triple backtick delimiters to prevent user content from overriding the agent's instructions.
  • Privacy & Data: There is no evidence of data exfiltration or hardcoded credentials. The skill focuses on processing local content to produce image assets within the user's specified directories.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM