The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of a local TypeScript script (clarity-check/clarity-check.ts) using the bun runtime and leverages the clarinet CLI to perform contract validation. These actions are consistent with the skill's stated purpose as a developer tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of Clarity smart contract source files, which presents a surface for indirect prompt injection.
Ingestion points: Contract files are ingested through the --source parameter in the validate and checklist subcommands.
Boundary markers: The skill generates structured JSON output, which serves as a delimiter to prevent the agent from misinterpreting data as instructions.
Capability inventory: The skill has the capability to read local files and execute specific scripts; it is explicitly described as read-only and lacks network or file-write capabilities.
Sanitization: No explicit sanitization of contract content is mentioned, but the use of structured output and static analysis methodology significantly limits the exploitation surface.

clarity-check