hive-network-infrastructure
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data from blockchain providers which could theoretically contain malicious instructions.
- Ingestion points: External data enters the agent context via blockchain RPC calls using
invoke_api_endpoint(SKILL.md). - Boundary markers: The skill enforces a structured 'Report template' and 'Evidence receipt' (SKILL.md), which helps differentiate evidence from instructions but lacks explicit 'ignore embedded instructions' prompts for chain data.
- Capability inventory: The skill utilizes
invoke_api_endpointfor data retrieval andsearch_toolsfor tool discovery (SKILL.md). - Sanitization: There are no specific instructions to sanitize or validate the content of transaction logs or receipts before processing (SKILL.md).
Audit Metadata