analyzing-competitor-tiktok-content-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from TikTok (captions, hashtags, and bios) to perform strategy analysis and hook identification.
- Ingestion points: External data is ingested through the output of the TikTok scrapers described in
SKILL.md. - Boundary markers: The instructions do not define clear boundaries or provide directives to the agent to ignore instructions that may be embedded within the scraped TikTok content.
- Capability inventory: The skill possesses capabilities to execute shell commands (
curl), run local scripts (node scripts/run_actor.js), and write output to the filesystem (--output). - Sanitization: The instructions do not specify any sanitization or filtering of the content retrieved from external TikTok profiles before it is processed by the agent.
- [DYNAMIC_EXECUTION]: The skill utilizes a local Node.js script to manage task execution and data processing.
- Evidence:
node scripts/run_actor.jsis invoked to run actors and handle data formatting. - [COMMAND_EXECUTION]: The skill uses shell-based commands for automation and data retrieval.
- Evidence: Workflow steps include the use of
curlfor REST API interactions andnodefor script execution. - [EXTERNAL_DOWNLOADS]: The skill retrieves data from a well-known external service.
- Evidence: Performs network requests to the Apify API (
api.apify.com) to fetch scraping results.
Audit Metadata