The Agent Skills Directory

[COMMAND_EXECUTION]: The skill proposes the execution of npm run format to the user as a final step to ensure consistent project formatting. This is a standard development practice and is contextually relevant to the skill's purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes content by reading source code and documentation from the repository to generate or update documentation. This represents a potential vulnerability surface where content in the repository could attempt to influence the agent's output.
Ingestion points: The skill reads files within the packages/ and docs/ directories (SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the skill instructions.
Capability inventory: The skill uses replace and write_file tools and suggests the command npm run format (SKILL.md).
Sanitization: There is no evidence of sanitization or filtering applied to the content read from the project files.

docs-writer