The Agent Skills Directory

[SAFE]: The skill is designed for knowledge retrieval and synthesis from a user-managed wiki. It includes explicit safety instructions that prevent the agent from scanning root directories or user home folders, which protects sensitive system and configuration files from accidental exposure.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from local wiki pages to generate answers, creating a surface for potential indirect prompt injection if the ingested notes contain instructions intended to override the agent's behavior. This risk is inherent to the primary purpose of reading user-provided content.
Ingestion points: The skill reads index.md, Overview.md, and specific markdown files targeted during the search workflow in SKILL.md.
Boundary markers: There are no explicit instructions for the agent to ignore commands or use specific delimiters when processing the content of wiki pages.
Capability inventory: The skill requires filesystem read access for knowledge gathering and filesystem write access for logging queries and creating new wiki pages at the user's request.
Sanitization: The skill does not implement text sanitization or instruction filtering for the content read from wiki files.

wiki-query