hive-token-diligence
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured workflow for token analysis, requiring exact contract addresses and providing detailed evidence receipts to ensure data provenance.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from blockchain providers, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Data returned from
invoke_api_endpointregarding token metadata, holders, and risk signals.\n - Boundary markers: Employs a structured 'Report template' and 'Evidence receipt' to clearly delineate external evidence from agent commentary.\n
- Capability inventory: Limited to informational tool calls (
search_tools,get_api_endpoint_schema,invoke_api_endpoint); no file-system modification or shell execution capabilities are exposed.\n - Sanitization: Relies on structured data formats (MCP responses) and metadata validation via the
_hiveobject.
Audit Metadata