The Agent Skills Directory

[SAFE]: The skill performs legitimate security analysis consistent with its stated purpose. It provides comprehensive reference guides for various blockchain environments (Solidity, Vyper, Solana, Move, TON, CosmWasm) to identify privileged entry points.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it is designed to ingest and analyze untrusted smart contract source code.
Ingestion points: The skill utilizes Read, Grep, and Glob tools to extract content from contract files (.sol, .vy, .rs, .move, .fc, .tact).
Boundary markers: The instructions do not provide explicit delimiters or instructions for the agent to ignore potentially malicious directions embedded in code comments or string literals within the analyzed files.
Capability inventory: The skill has access to Bash (for executing the Slither analysis tool), Read, Grep, and Glob. It does not have wide-ranging network access or the ability to exfiltrate data to arbitrary domains.
Sanitization: There is no evidence of pre-processing or filtering of the ingested source code to remove potential injection vectors before analysis.
[COMMAND_EXECUTION]: The skill executes slither, a well-known open-source static analysis tool for Solidity, via the Bash tool. This is a local execution of a standard security utility and does not involve downloading or executing unverifiable remote scripts.

entry-point-analyzer