douyin-viral-content

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill identifies and processes historical content, which introduces a vulnerability surface. Evidence: 1. Ingestion points: Reads all markdown files in the '已发布/' directory and user-provided text. 2. Boundary markers: None. 3. Capability inventory: File read/write restricted to local project folders. 4. Sanitization: None.
  • No Code (SAFE): No scripts or binaries are included with the skill.
  • Data Exposure & Exfiltration (SAFE): No access to sensitive system paths or external network communication was detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:31 PM