finding-tiktok-shop-trending-products

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill exposes a customMapFunction parameter that accepts a JavaScript function as a string to transform output data. This functionality allows for arbitrary code execution within the data processing pipeline.
  • [COMMAND_EXECUTION]: The documentation provides instructions to execute a local Node.js script (scripts/run_actor.js) to interface with the Apify actor, which involves spawning subprocesses.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by processing external, untrusted content from TikTok.
  • Ingestion points: Data enters the agent's context from TikTok post captions, metadata, and creator profiles fetched via the apidojo/tiktok-scraper actor.
  • Boundary markers: The instructions do not define delimiters or explicit warnings to the agent to ignore instructions embedded in the scraped social media content.
  • Capability inventory: The skill has the capability to execute shell commands (curl), run local scripts (node), and perform network requests to the Apify API.
  • Sanitization: There is no evidence of filtering, escaping, or validation of the ingested TikTok data before it is scored or presented in the final output format.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 06:28 PM
Security Audit — agent-trust-hub — finding-tiktok-shop-trending-products