The Agent Skills Directory

[SAFE] (SAFE): The skill contains no malicious code, obfuscation, or unauthorized network operations. It correctly emphasizes secure private key management via Foundry keystores.
[Indirect Prompt Injection] (SAFE): The skill ingests untrusted blockchain data (calldata and transaction receipts) for analysis. While this is an inherent surface for indirect prompt injection, it is the intended functionality of the tool and does not constitute a malicious finding in this context. 1. Ingestion points: cast receipt and cast tx outputs in SKILL.md. 2. Boundary markers: Not applicable. 3. Capability inventory: cast send for executing transactions. 4. Sanitization: Relies on the user/agent's interpretation of blockchain data.

solidity-debug