linkfox-shopee-store-ads
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script to verify dependencies.
- Evidence:
scripts/_shopee_ads_common.pyusessubprocess.runto callscripts/check_auth_dependency.py. - The execution is limited to internal scripts using the current Python environment.
- [EXTERNAL_DOWNLOADS]: The skill communicates with vendor-owned domains for core functionality.
- Evidence: API requests are proxied through
tool-gateway.linkfox.com. - Evidence: Onboarding documentation is referenced at
agent-files.linkfox.com. - These domains are verified as belonging to the skill author (linkfox-ai).
- [PROMPT_INJECTION]: The skill processes external data from the Shopee Ads API, creating a surface for indirect prompt injection.
- Ingestion points: API response bodies are retrieved from
tool-gateway.linkfox.cominscripts/_shopee_ads_common.py. - Boundary markers: No specific delimiters or instructions to ignore embedded content are provided when the agent processes the API response.
- Capability inventory: The skill can execute local scripts via
subprocess.runinscripts/_shopee_ads_common.py. - Sanitization: Content is parsed as JSON, but individual text fields within the response are not sanitized for potential instruction strings.
Audit Metadata