The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external project files and documentation using tools like Read, Glob, and Grep. It has high-privilege capabilities including shell execution via Bash and file system modification via Write and Edit. The instructions do not define boundary markers or sanitization protocols for content read from the project environment, creating a potential surface where malicious instructions embedded in project files could influence agent behavior. * Ingestion points: Architecture Decision Records (ADRs), performance logs, and project files accessed through Read, Glob, and Grep tools. * Boundary markers: Absent; there are no instructions to use delimiters or to disregard instructions found within the data being processed. * Capability inventory: Shell command execution (Bash) and file writing/editing (Write, Edit). * Sanitization: Absent; no specific validation, filtering, or escaping of input data is defined.

game-technical-director