The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from various project files to generate a test protocol, creating a surface for indirect prompt injection.
Ingestion points: The skill reads data from .claude/docs/technical-preferences.md, design/gdd/game-concept.md, and the most recent files in production/playtests/ and production/qa/ (Phase 2 of SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded instructions within the ingested files are present.
Capability inventory: The skill utilizes the Read, Glob, Grep, and Write tools to interact with the file system.
Sanitization: No evidence of sanitization or content validation for the read files was found.

soak-test