The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js script located at scripts/run-state-check.js. This is used to verify the current state of the distribution analysis before proceeding and is a standard operational procedure within this skill's context.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external data concerning Ideal Customer Profile (ICP) and community evidence to make distribution decisions. This represents an ingestion surface for potentially untrusted data.
Ingestion points: Data extracted from the run-state command, ICP definitions, and community reach lists.
Boundary markers: The instructions do not define specific delimiters for separating user-provided evidence from system instructions.
Capability inventory: The skill is restricted to analytical decision-making; it lacks tools for network operations or file system writes in the provided definition.
Sanitization: There is no evidence of input validation or sanitization for the processed evidence.

distribution