travel-postcard-agent
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, or obfuscation, were detected in any of the skill files.
- [EXTERNAL_DOWNLOADS]: The skill uses web search capabilities to verify real-world facts like festival dates and coordinates. This is a documented functional requirement and does not involve downloading or executing untrusted code.
- [PROMPT_INJECTION]: The instructions contain clear boundaries for the agent's behavior, focusing strictly on prompt generation and explicitly avoiding unrelated tasks like travel planning or general Q&A.
- [DATA_EXFILTRATION]: There are no patterns indicating access to sensitive local files or unauthorized network communication. Data processing is limited to public geographic and cultural information.
Audit Metadata