The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes content from Obsidian note history and sync versions, creating a surface for indirect prompt injection where malicious instructions embedded in a note could attempt to influence the agent's behavior.\n
Ingestion points: Note content is retrieved using the obsidian history:read, obsidian sync:read, and obsidian diff commands described in SKILL.md.\n
Boundary markers: The skill does not implement delimiters or explicit instructions to isolate retrieved note content from the agent's instruction context.\n
Capability inventory: The agent's capabilities are limited to Bash (restricted to the obsidian CLI), Read, Grep, and Glob.\n
Sanitization: There is no evidence of sanitization or filtering for note content retrieved from history stores.

file-history