The Agent Skills Directory

[COMMAND_EXECUTION]: The SKILL.md file contains instructions for the agent to execute a cat command to read .claude/context/memory/learnings.md. This is a documented pattern for state management and context retrieval in specific agent environments.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads and analyzes external tsconfig.json files which could contain malicious instructions embedded in comments or string values.
Ingestion points: tsconfig.json files identified via the globs pattern in the skill configuration.
Boundary markers: There are no explicit markers or instructions provided to the agent to help it distinguish between data content and potential instructions within the processed files.
Capability inventory: The skill is configured with Read, Write, and Edit tools, granting it the ability to modify files in the repository.
Sanitization: No explicit sanitization or validation of the tsconfig.json content is performed before the model processes the file.

tsconfig-json-rules