The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were identified in the skill definitions or instructions.
[COMMAND_EXECUTION]: The skill utilizes file management tools (Read, Write, Edit, Grep, Glob) to assess and modify note content within an Obsidian vault, which is consistent with its stated curation purpose.
[PROMPT_INJECTION]: The skill processes markdown files from the Obsidian vault, which serves as an ingestion point for potentially untrusted data. Ingestion points: Markdown file content and titles (SKILL.md). Boundary markers: Absent. Capability inventory: Read, Write, Edit, Grep, Glob tools (SKILL.md). Sanitization: Absent. This surface allows for indirect prompt injection, although the lack of network tools limits the threat of exfiltration.

content-curator