The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted Solidity source code for security auditing, which introduces a potential attack surface. * Ingestion points: The skill triggers on tasks involving smart contract review and security audits as defined in the skill metadata. * Boundary markers: The instructions do not explicitly define specific delimiters (e.g., XML tags or unique markers) to isolate external code from the agent's reasoning instructions. * Capability inventory: The skill utilizes powerful static analysis tools via MCP, including run_slither, run_aderyn, and match_vulnerability_patterns, which may execute commands on the host environment. * Sanitization: There are no explicit instructions for sanitizing or escaping the content of the smart contracts before processing.
[SAFE]: The skill focuses on industry-standard security best practices (such as Checks-Effects-Interactions and Reentrancy protection) and utilizes recognized security analysis tools. The instructions are aligned with established audit methodologies and do not contain any evidence of malicious intent, obfuscation, or unauthorized data access.

solidity-code-review