skill-05-dao-governance
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core functionality of processing external data.
- Ingestion points: The skill is instructed to analyze and report on governance proposal descriptions, executable calls, and metadata (SKILL.md, Analysis section).
- Boundary markers: The instructions lack specific boundary markers or delimiters to isolate untrusted proposal content from the agent's instructions.
- Capability inventory: The skill has significant capabilities, including interacting with smart contracts for proposal submission and execution via the blockchain-rpc-server and defi-protocol-server MCPs.
- Sanitization: No procedures are specified for validating or sanitizing external proposal content before it is processed by the agent.
Audit Metadata