The Agent Skills Directory

[SAFE]: The skill defines a standard workflow for interacting with the Obsidian Bases plugin. Its behavior is consistent with its stated purpose of research and knowledge management.
[EXTERNAL_DOWNLOADS]: The skill references documentation from a public repository on GitHub (github.com/kepano/obsidian-skills). This repository belongs to a well-known figure in the Obsidian development community and is considered a reputable source.
[DATA_EXFILTRATION]: The skill instructs the agent to read file metadata (e.g., tags, paths, sizes) and frontmatter properties. This data access is confined to the local environment and is required for filtering and displaying notes within the application. No network operations targeting non-whitelisted domains were found.
[PROMPT_INJECTION]: There are no instructions that attempt to override the model's safety constraints, extract system prompts, or bypass content guidelines. The guidance is strictly technical and focused on YAML syntax and formula logic.
[COMMAND_EXECUTION]: The skill does not use shell commands, subprocesses, or any form of arbitrary command execution. It relies entirely on structured data configuration.

obsidian-bases