hive-stateful-monitoring
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration were detected. The skill's primary purpose is persistent monitoring of crypto assets, which it performs using structured vendor tools.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests user-defined rules and external blockchain data for monitoring. However, the instructions mitigate this risk by mandating explicit user approval before any creation or update action (
invoke_stateful_endpoint) and requiring a detailed evidence receipt for every material response. - [EXTERNAL_DOWNLOADS]: The documentation references
hive-mcp-clientas a standard Node.js dependency for B2B implementations. This is a recognized vendor resource for the platform. - [DATA_EXPOSURE]: The skill handles sensitive B2B subject context and signing headers. The instructions correctly identify these as server-side responsibilities and explicitly forbid accepting these values from prompt content, protecting against spoofing and unauthorized access.
Audit Metadata