The Agent Skills Directory

[SAFE]: The skill operates entirely within the local file system to perform its primary function of wiki auditing. No external network requests, obfuscation, or hardcoded credentials were found.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes content from user-controlled wiki pages.
Ingestion points: Processes content from wiki/index.md, wiki/overview.md, and all markdown files in wiki/pages/ as specified in SKILL.md.
Boundary markers: Absent; there are no specific markers used to distinguish wiki content from system instructions during processing.
Capability inventory: The skill has the capability to write new files (wiki/pages/lint-<today>.md) and modify existing ones (wiki/index.md, wiki/log.md). No shell execution or network capabilities are present.
Sanitization: Absent; the skill does not explicitly sanitize or escape the content read from the wiki before including it in the generated reports.

wiki-lint