finding-tiktok-creators-using-trending-sounds

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill documentation describes a customMapFunction input parameter that accepts a string representing a JavaScript function. This function is intended to transform output objects on the Apify platform, which constitutes dynamic code execution at runtime.
  • [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands using node scripts/run_actor.js and curl. These commands interact with external APIs and local scripts to perform data scraping tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from TikTok (usernames, hashtags, post metadata). This creates a surface for indirect prompt injection if the scraped content contains malicious instructions that could influence the agent's behavior during the scoring or summarization phases.
  • Ingestion points: TikTok music/sound page URLs processed by the Apify actor.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Execution of local node scripts and network requests via curl.
  • Sanitization: No explicit sanitization of the scraped data is mentioned before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 07:51 PM
Security Audit — agent-trust-hub — finding-tiktok-creators-using-trending-sounds