support-brief
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of plain-text instructions for summarizing existing conversation context. No malicious code or obfuscation was detected.
- [DATA_EXPOSURE]: The skill instructs the agent to verify information against sources such as Stripe or databases mentioned in the conversation. It does not include tools or credentials to access these services directly, and it does not perform any data exfiltration.
- [PROMPT_INJECTION]: There are no instructions designed to bypass safety filters, override system prompts, or extract sensitive instructions.
Audit Metadata