linkfox-shopee-store-ads
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with vendor-managed API endpoints at
tool-gateway.linkfox.com,api.linkfox.com, andagent-api.linkfox.comfor Shopee Ads proxying and account management (onboarding). These are legitimate vendor resources used for the skill's primary function. - [COMMAND_EXECUTION]: The helper script
scripts/_shopee_ads_common.pyusessubprocess.runto execute a local dependency checker (check_auth_dependency.py). This execution is restricted to the skill's internal directory and uses the current Python interpreter, posing no risk of arbitrary command injection. - [INDIRECT_PROMPT_INJECTION]: The skill processes structured JSON data from external Shopee Ads APIs.
- Ingestion points: Data is fetched via
urllib.request.urlopeninscripts/_shopee_ads_common.pyand processed inscripts/_ads_api_runner.py. - Boundary markers: The skill relies on standard JSON parsing and does not explicitly use delimiters for the resulting data, though it primarily extracts specific fields for display.
- Capability inventory: Subprocess calls are restricted to internal environment checks; no arbitrary code execution or file-system write capabilities are exposed to the ingested data.
- Sanitization: The skill uses standard JSON decoding to handle API responses.
Audit Metadata