douyin-viral-breakdown
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of natural language instructions within a markdown file and does not include any scripts, executable programs, or tool configurations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data such as video titles and transcriptions which could contain malicious instructions. However, the risk is mitigated as the skill lacks actionable capabilities. 1. Ingestion points: Douyin JSON metadata and transcriptions as described in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No command execution, network access, or file-writing tools are defined or referenced. 4. Sanitization: Not applicable as the skill performs analysis only.
Audit Metadata