The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from the user's Obsidian vault, which may include untrusted data such as clipped articles or external research notes containing malicious instructions.\n
Ingestion points: The skill uses Read and mcp__obsidian__read-note to retrieve file content from the vault (SKILL.md).\n
Boundary markers: No explicit delimiters or instructions are provided to distinguish between data and instructions within the processed notes.\n
Capability inventory: The skill allows access to Bash, Write, and Edit tools (SKILL.md), which could be leveraged if the agent is manipulated by instructions found in a note.\n
Sanitization: There is no evidence of sanitization or filtering of note content before it is processed for metadata extraction or body updates.

obsidian-note