The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run development commands such as pnpm lint, pnpm tsc, and pnpm test to validate code changes. This is standard practice for maintaining project integrity and is explicitly documented in SKILL.md and checklists/post-simplify.md.
[DATA_INGESTION_SURFACE]: The agent ingests and processes user-provided source code to perform its core function of simplification, which creates an inherent surface for indirect prompt injection.
Ingestion points: The agent reads source files within the project scope as described in SKILL.md and checklists/pre-simplify.md.
Boundary markers: No specific boundary markers or 'ignore' instructions are defined to separate code logic from potential embedded instructions.
Capability inventory: The agent has filesystem write access through the Edit tool and command execution capabilities for project tooling.
Sanitization: There is no mention of sanitizing the input code to filter out potential injection attacks.

code-simplifier