china-customer-research

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill primarily consists of instructional markdown files providing a methodology for market research. No executable code, malicious scripts, or system-level commands were detected.
  • [DATA_EXPOSURE]: The skill instructs the agent to read project-specific context files (e.g., .agents/product-marketing.md and product-marketing-context.md). These are standard locations for project documentation and do not involve sensitive system files or credentials.
  • [PROMPT_INJECTION]: The instructions are designed to guide agent behavior for research purposes. There are no patterns suggesting attempts to bypass AI safety filters or hijack the underlying system prompt.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to browse well-known public platforms and communities for research. It includes strict rules against bypassing paywalls, login restrictions, or using unauthorized tokens/cookies, significantly reducing the risk of unauthorized data access.
  • [SAFE]: The 'references/source-quality.md' file specifically mandates de-identification of personal information and adherence to platform terms of service, aligning with security and privacy best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 03:04 AM
Security Audit — agent-trust-hub — china-customer-research