The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The refactoring process requires the agent to ingest and analyze untrusted external data (source code and tests), which creates an attack surface for indirect prompt injection.\n
Ingestion points: The skill specifies reading target code, its callers, and nearby tests (SKILL.md, Step 1).\n
Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the target code are provided.\n
Capability inventory: The skill utilizes the ability to run build and test tools including typecheck, tests, lint, and build (SKILL.md, Step 4).\n
Sanitization: The instructions do not include steps to sanitize or validate the content of the ingested files.\n- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute repository-specific tools and checks.\n
Evidence: Directions to run typecheck, tests, lint, and build commands are included in the verification steps (SKILL.md, Step 4).

refactor