money
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define an architecture where the agent processes untrusted data from blockchain events and P2P mesh nodes.
- Ingestion points: Untrusted data enters the agent context via ERC-20 transfer events, withdrawal events, governance proposals, and P2P GossipSub topics described in the wiring section of SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from following instructions embedded in the external data.
- Capability inventory: The agent is configured with tools to interact with financial systems including treasury management, governance voting, and staking operations.
- Sanitization: No description of data sanitization or validation is present in the skill manifest for the ingested event data.
Audit Metadata