The Agent Skills Directory

[SAFE]: The skill consists exclusively of markdown instructions and guidelines for documentation maintenance. It describes internal project file structures and naming conventions without requesting sensitive information or external network access.
[INDIRECT_PROMPT_INJECTION]: The skill involves reading local repository files (such as .d.ts files and existing markdown documentation) to inform the generation of new documentation snippets. While this creates a surface where the agent could ingest untrusted data if those source files were compromised, the risk is inherent to the intended documentation-writing task and the skill does not grant the agent high-privilege capabilities to act on that data beyond writing text.
Ingestion points: docs/*.md, web/wasm/**/*.d.ts
Boundary markers: Absent
Capability inventory: Reading local source files and writing markdown content.
Sanitization: Absent

navara-add-docs-example