Skills
skills/kadel/claude-plugins/obsidian-knowledge-base/Gen Agent Trust Hub

obsidian-knowledge-base

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the ingestion of local files.
  • Ingestion points: The file Knowledge Base.md located at the root of the Obsidian vault (SKILL.md).
  • Boundary markers: Absent. The skill instructions explicitly state that this file is the 'single source of truth for all conventions, operations, frontmatter rules, page templates, and naming conventions,' which directs the agent to follow instructions found within that file without isolation.
  • Capability inventory: The skill uses the Bash tool (for vault and read operations) and the Read tool (SKILL.md).
  • Sanitization: Absent. There are no instructions to sanitize or validate the content of the knowledge base file before the agent adopts its conventions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 03:46 PM