The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the wiki pages and configuration files (AGENTS.md, CLAUDE.md) to perform its linting tasks.
Ingestion points: The agent reads Markdown files and schema configuration files from the local project directory.
Boundary markers: No explicit boundary markers or "ignore instructions" directives are used when the agent reads these files.
Capability inventory: The agent is instructed to report findings and, upon user authorization, apply fixes (file writes) to the wiki files.
Sanitization: Content is processed using regular expressions for link validation; no specific sanitization for malicious instructions within the wiki content is implemented.
[DYNAMIC_EXECUTION]: The regression test suite (scripts/test_check_wiki.py) utilizes the importlib library to dynamically load the core logic from check_wiki.py. This is a standard practice for unit testing Python scripts that are not part of a formal package.
[COMMAND_EXECUTION]: The test suite invokes the skill's own CLI interface using subprocess.run to verify expected behavior and error handling. The execution is limited to the bundled Python script and uses controlled arguments without shell interpolation.

wiki-lint