The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes raw notes from a user-provided path during the 'Analyze Mode'. This data enters the agent's context without explicit boundary markers or sanitization, creating a surface for indirect prompt injection where instructions hidden within the notes could attempt to influence the agent's logic or subsequent tasks.
Ingestion points: Raw playtest notes loaded from a user-specified path via the analyze [path] command.
Boundary markers: Absent; the instructions do not define clear delimiters or provide the agent with a 'treat as data only' directive for the notes.
Capability inventory: The skill possesses the Write tool (enabling file creation) and the Task tool (enabling the spawning of a 'creative-director' agent).
Sanitization: Absent; the skill does not perform any validation or filtering on the content of the raw notes before processing them.

playtest-report