linkfox-shopee-store-account-health
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/_shopee_account_health_common.pyusessubprocess.runto execute a local python script (check_auth_dependency.py) for dependency verification. This is a controlled execution of the skill's own components and does not use a shell, minimizing injection risks. - [INDIRECT_PROMPT_INJECTION]: The skill processes external store data from Shopee's API gateway. While this exposes an attack surface where malicious remote data could attempt to influence the agent, the skill implements mitigations to manage this risk.
- Ingestion points: API responses processed in
scripts/_account_health_api_runner.py. - Boundary markers: Implements a response size threshold (8 KB), switching to a summary mode for larger data sets to reduce context exposure.
- Capability inventory: Local file writing, network requests to vendor domains, and local command execution for environment checks.
- Sanitization: None. External data is merged into the JSON result without content-level sanitization.
Audit Metadata