The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its log-reading capabilities.
Ingestion points: debug_get_logs and debug_get_stack_trace ingest data from the Unity console, which can contain output from any running script or third-party asset.
Boundary markers: There are no specified delimiters or instructions to treat log content as untrusted data in the skill's prompt logic.
Capability inventory: The skill possesses the ability to modify project configuration via debug_set_defines and trigger system-heavy operations like debug_force_recompile (which triggers a domain reload).
Sanitization: No sanitization or validation of log content is described before it is processed by the agent, allowing potential malicious instructions in log messages to influence subsequent agent actions.

unity-debug