scraping-tiktok-posts-by-music

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill defines a customMapFunction input parameter which accepts a JavaScript function as a string. This string is intended to transform output data, representing a dynamic code execution capability where logic is provided at runtime.
  • [COMMAND_EXECUTION]: The documentation provides instructions for executing local shell commands using node scripts/run_actor.js and curl. The skill relies on the presence of a local script (scripts/run_actor.js) that is not included in the analyzed file.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes untrusted content from external TikTok URLs.
  • Ingestion points: External TikTok sound pages and post data (captions, hashtags) are retrieved via the startUrls parameter.
  • Boundary markers: The skill does not specify any delimiters or instructions to prevent the agent from interpreting embedded content in the scraped data as instructions.
  • Capability inventory: The skill can execute local scripts via node and perform network operations via curl and the Apify API.
  • Sanitization: There is no mention of sanitization or filtering of the scraped TikTok content before it is returned to the agent context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 07:07 PM
Security Audit — agent-trust-hub — scraping-tiktok-posts-by-music