mev-bot-infrastructure-analysis-agent
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as an instructional framework for blockchain forensics and research, containing no executable code or scripts. All referenced data sources are public blockchain explorers and analytics platforms.
- [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized network operations was detected. The instructions prioritize ethical research and the use of documented APIs.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a vulnerability surface by processing untrusted blockchain data such as searcher addresses and bundle IDs. Evidence chain: 1. Ingestion points: User-supplied searcher addresses and bundle identifiers in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Instructions to utilize external analytics platforms like Dune and Jito. 4. Sanitization: Not mentioned.
Audit Metadata