linkfox-shopee-store-discount

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external Shopee API responses and provides summaries to the agent. This represents an indirect prompt injection surface where untrusted data could attempt to influence the agent's behavior.
  • Ingestion points: External API response data retrieved through developer_proxy_call and processed by the emit_result function in scripts/_shopee_discount_common.py.
  • Boundary markers: No explicit delimiters or boundary markers are used when outputting API content to the agent context.
  • Capability inventory: The skill possesses file system write capabilities (via emit_result writing to local JSON files) and subprocess execution capabilities (used for the dependency check).
  • Sanitization: The skill relies on standard JSON serialization for outputting data.
  • [COMMAND_EXECUTION]: The skill executes a local dependency check using subprocess.run to verify the presence of a required authentication skill. The execution is performed using a list of arguments with the current Python interpreter, which is a secure implementation method.
  • [DATA_EXFILTRATION]: The skill transmits API keys and user authentication data (such as phone numbers and login codes during the onboarding process) to vendor-controlled domains including tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com. These operations are consistent with the skill's documented purpose for authentication and API proxying.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:03 AM
Security Audit — agent-trust-hub — linkfox-shopee-store-discount