The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides shell command templates using find and grep to search for files and content within the local directory /mnt/d/Obsidian Vault/AI Research/. These commands are standard for file management and search workflows.
[PROMPT_INJECTION]: The skill interacts with the content of external Markdown files, which constitutes an indirect prompt injection surface. Instructions embedded in notes could potentially be interpreted by the agent during search or read operations.
Ingestion points: Filenames and note contents retrieved from the local vault via find and grep as described in SKILL.md.
Boundary markers: None specified in the workflow instructions.
Capability inventory: The skill demonstrates read capabilities using standard CLI tools; no network or administrative capabilities are present.
Sanitization: No sanitization or filtering of note content is mentioned before it is processed by the agent.
[SAFE]: No malicious patterns, such as hardcoded credentials, data exfiltration to remote servers, or obfuscated scripts, were detected in the analyzed files.

obsidian-vault