tiktok-analytics
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of external, untrusted content from TikTok video descriptions.\n
- Ingestion points: Data is scraped from TikTok profile pages and creator analytics dashboards via the browser.\n
- Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' prompts when processing scraped text.\n
- Capability inventory: The skill uses browser automation tools (navigation, JS execution) and has the ability to append data to local files (content-performance.md).\n
- Sanitization: There is no evidence of sanitizing or validating the scraped descriptions before they are used for categorization or recommendations.
Audit Metadata