jb-obsidian-sync

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external Obsidian Markdown files, which introduces a potential surface for instructions within the data to influence the agent's behavior.
  • Ingestion points: Markdown notes within the Obsidian vault checkouts (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or specific prompts to ignore instructions found within note content.
  • Capability inventory: The agent is authorized to use the ob CLI for vault operations and standard utilities like rg, find, and grep for searching and reading files (SKILL.md).
  • Sanitization: No specific sanitization or validation of the ingested note content is prescribed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:52 PM
Security Audit — agent-trust-hub — jb-obsidian-sync