The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the eslint --print-config command to resolve and evaluate the project's effective linting configuration. This is a standard and task-specific use of a common developer tool.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests untrusted content from the project repository (such as README files, commit messages, and configuration files) to inform its routing decisions and draft content.
Ingestion points: The skill reads README.md, CONTRIBUTING.md, configuration files like eslint and tsconfig, and the git commit history.
Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore or isolate potential instructions embedded within the scanned files.
Capability inventory: The skill is capable of performing filesystem writes (creating/modifying documentation and config files), executing local commands, and delegating tasks to other writing skills.
Sanitization: There is no evidence of content validation or sanitization of the data retrieved from the repository before it is processed by the agent.

codify