Skills
Navigate
skills/linkfox-ai/linkfox-skills/linkfox-multimodal-product-similarity/Gen Agent Trust Hub

linkfox-multimodal-product-similarity

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill communicates with vendor-controlled API endpoints at tool-gateway.linkfox.com, api.linkfox.com, agent-api.linkfox.com, and skill-api.linkfox.com. These are legitimate resources used for product analysis, account management, and providing feedback.
  • [COMMAND_EXECUTION]: Operates via Python scripts to interface with the analysis API. scripts/multimodal_analyze_product_similarity.py handles the primary analysis logic and local result caching, while scripts/onboarding.py facilitates user authentication and environment configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted product data (refResultData) from preceding tasks. Evidence chain:
  • Ingestion points: refResultData and userInput in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Network POST requests via urllib.request and local file writes to the linkfox/ directory.
  • Sanitization: Absent; data is handled as structured JSON for transmission to the vendor's backend API.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 03:10 AM