linkfox-shopee-store-livestream

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/_shopee_livestream_common.py executes a local Python script scripts/check_auth_dependency.py using subprocess.run. This is used to verify that the required linkfox-shopee-store-auth skill is available in the environment.
  • [PROMPT_INJECTION]: The skill provides functionality to fetch live comments from Shopee (get_latest_comment_list.py). Since these comments are generated by external users, they represent an indirect prompt injection vector if the agent processes them without strict context isolation.
  • Ingestion points: Data enters the context through the get_latest_comment_list API response handled in scripts/get_latest_comment_list.py.
  • Boundary markers: None identified; the response JSON is printed directly to stdout or saved to disk.
  • Capability inventory: The skill allows for file writing to the local workspace and subsequent network calls to manage comments and items.
  • Sanitization: No specific sanitization or filtering of comment content is performed before presentation to the agent.
  • [EXTERNAL_DOWNLOADS]: The scripts/onboarding.py script checks for and requests the manual installation of third-party libraries requests, qrcode, and pillow to support login and payment QR code generation.
  • [SAFE]: The skill interacts exclusively with the vendor's domains (tool-gateway.linkfox.com, api.linkfox.com, agent-api.linkfox.com) for API proxying and account management, which is consistent with its stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:03 AM
Security Audit — agent-trust-hub — linkfox-shopee-store-livestream