The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests Unity Editor console logs which are often populated by untrusted external data, such as network responses, third-party plugin outputs, or user-supplied strings logged by the application.
Ingestion points: The console_get_logs skill in SKILL.md allows the agent to read log messages and stack traces from the Unity console.
Boundary markers: There are no instructions provided to the agent to treat log content as untrusted data or to ignore instructions embedded within the logs.
Capability inventory: The skill environment includes file-writing capabilities via the console_export skill, which accepts a savePath parameter.
Sanitization: There is no evidence of log content sanitization or validation before it is interpolated into the agent's context.

unity-console