linkfox-tiktok-shop-product-detail

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from TikTok Shop via the LinkFox API and includes it in the agent's context. This represents an indirect prompt injection surface if the product metadata contains malicious instructions.
  • Ingestion points: Data is fetched by scripts/tiktok_shop_product_detail.py from https://tool-gateway.linkfox.com.
  • Boundary markers: The script implements a threshold-based summarization strategy (8KB) and writes full responses to disk to prevent context flooding.
  • Capability inventory: The skill has the ability to execute network requests and write to the local file system within the project directory.
  • Sanitization: Content is processed as structured JSON; the skill instructions suggest using jq for targeted field extraction rather than ingesting raw full responses.
  • [COMMAND_EXECUTION]: The skill relies on local Python scripts (scripts/tiktok_shop_product_detail.py and scripts/onboarding.py) to perform its core functions. These scripts are invoked via shell commands to interact with vendor APIs and manage local data files.
  • [EXTERNAL_DOWNLOADS]: The scripts/onboarding.py script suggests the installation of standard third-party Python libraries (requests, qrcode, pillow) if they are missing from the environment. These are well-known packages used for HTTP communication and QR code generation for the payment onboarding flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:04 PM
Security Audit — agent-trust-hub — linkfox-tiktok-shop-product-detail