The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external files and state directories which constitutes an attack surface where malicious instructions could be embedded in data.
Ingestion points: The skill reads from production/session-state/ for continuity and references project documents like @docs/collaboration-protocol.md, @docs/coordination-rules.md, and @docs/agent-hierarchy.md.
Boundary markers: There are no explicit instructions to use delimiters or warnings to ignore embedded commands within the ingested project files.
Capability inventory: The skill is permitted to use Write and Edit tools to modify project files, alongside Read, Glob, Grep, and AskUserQuestion.
Sanitization: No specific sanitization, filtering, or validation logic is described for the content read from the filesystem before it is processed by the agent.

game-producer