skills/dcoon/agent-kit/notebook/Gen Agent Trust Hub

notebook

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process content from a local Obsidian vault, which creates a surface for indirect prompt injection where instructions embedded in notes could influence the agent's behavior.
  • Ingestion points: The skill reads from journal entries (e.g., journal/YYYY-MM-DD.md) and other vault pages to extract entity information.
  • Boundary markers: The skill uses Markdown headings as structural delimiters for sections, but it lacks explicit instructions to the agent to ignore or isolate potential instructions embedded within the user-provided text content.
  • Capability inventory: The agent is granted the ability to read, write, append, and patch files in the local filesystem through the obsidian-mcp server or direct file access tools.
  • Sanitization: There are no defined procedures for sanitizing, filtering, or validating the content extracted from the notebook before it is processed or used to update other notes.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 05:23 PM