monitoring-tiktok-mentions-of-brand

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill supports a customMapFunction input parameter that accepts a JavaScript function string. This string is executed at runtime to transform scraped data, creating a surface for dynamic code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-generated content from TikTok (captions and comments), which may contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: TikTok video captions, comments, and creator metadata retrieved via the apidojo/tiktok-scraper actor (SKILL.md).
  • Boundary markers: The monitoring report template lacks explicit delimiters or instructions to the agent to ignore potentially malicious content embedded within the scraped text.
  • Capability inventory: The skill employs shell commands via node and curl to execute scraping tasks and generate reports (SKILL.md).
  • Sanitization: No specific sanitization, filtering, or validation steps are documented for the external TikTok content before it is processed and presented in the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:26 PM
Security Audit — agent-trust-hub — monitoring-tiktok-mentions-of-brand