The Agent Skills Directory

[SAFE]: The skill serves as a legitimate technical guide for smart contract auditing and does not contain malicious instructions or payloads.
[COMMAND_EXECUTION]: Provides standard grep commands for static code analysis and environment verification checks (e.g., which solc), which are routine for security professionals.
[EXTERNAL_DOWNLOADS]: Mentions well-known and trusted blockchain infrastructure providers like Etherscan and Solscan for manual verification.
[INDIRECT_PROMPT_INJECTION]: As the skill processes untrusted smart contract source code, it possesses an inherent risk of indirect prompt injection from the code being audited; however, this is a standard risk for auditing tools and is documented with neutral security posture.

meme-coin-audit