The Agent Skills Directory

[SAFE]: The skill provides formatting guidelines for Obsidian-specific markdown syntax across SKILL.md and REFERENCE.md. It contains no executable code, scripts, or runtime logic.\n- [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety guidelines, or extract system prompts were detected in the instructions or metadata.\n- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, package installations, or unverifiable dependencies were found. All external links are references to official documentation (e.g., obsidian.md, commonmark.org, github.com).\n- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file access patterns, or unauthorized network operations are present. The skill's tool use (Read, Write, Edit) is limited to the intended purpose of managing Markdown files.\n- [INDIRECT_PROMPT_INJECTION]: While the skill facilitates reading and writing .md files (which could theoretically contain instructions), it functions solely as a syntax guide and does not introduce specific vulnerable interpolation or ingestion logic beyond standard file operations.

obsidian-markdown