daemon-intelligence
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or data exfiltration attempts were found within the documentation or instruction files.
- [EXTERNAL_DOWNLOADS]: The documentation references the '@xyflow/react' Node.js package as a dependency for rendering blockchain graph data, which is a standard industry practice for frontend visualization.
- [PROMPT_INJECTION]: The skill facilitates the ingestion of external data from web searches and blockchain audits, creating a potential surface for indirect prompt injection. 1. Ingestion points: 'v1/agent/discover' (Exa search results) and MCP tool results from 'daemon-intel', 'exa', and 'arkham-analytics'. 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are included in the provided prompt templates. 3. Capability inventory: No local script execution or file system write capabilities are present in the skill files. 4. Sanitization: No explicit sanitization or validation of the external content is described. This behavior is consistent with the primary purpose of an AI agent backend, and no local execution capabilities are exposed.
Audit Metadata