obsidian-markdown
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official Obsidian documentation from
help.obsidian.mdto provide the agent with additional context on Markdown syntax. - [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing and generating Obsidian Markdown files, which creates a potential surface for indirect prompt injection if external note content contains malicious instructions.
- Ingestion points: Obsidian Markdown files (.md) and their YAML frontmatter properties.
- Boundary markers: Absent; there are no specific instructions for the agent to use delimiters or ignore instructions found within processed notes.
- Capability inventory: None; the skill contains no executable scripts, shell commands, or network operations.
- Sanitization: Absent; no sanitization or validation logic is provided for the content of processed notes.
Audit Metadata