obsidian-note-builder
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
findandgrepin the 'Workflow' section of SKILL.md to analyze the local Obsidian vault's structure, naming conventions, and tag taxonomy. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8) by ingesting untrusted data like brain dumps, transcripts, and web article excerpts to perform entity extraction and note structuring.
- Ingestion points: External content provided by the user (summaries, excerpts, transcripts) as described in the 'When to Use' and 'Workflow' sections of SKILL.md.
- Boundary markers: None; the skill does not utilize delimiters or specific instructions to isolate untrusted content from the agent's core instructions.
- Capability inventory: The agent has permissions to read the local filesystem via shell tools and create/write markdown files.
- Sanitization: None; there is no mention of validating, escaping, or filtering the ingested data before it is processed by the model.
Audit Metadata