logseq-organization

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process, format, and modify content within the user's Logseq vault. This creates a surface for indirect prompt injection if external content or untrusted data is saved into these notes and subsequently processed by the agent.
  • Ingestion points: The agent reads and interacts with Markdown files in the journals/ and pages/ directories.
  • Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions embedded within the notes being processed.
  • Capability inventory: The skill grants the agent the ability to create and modify local files within the specified vault directory structure.
  • Sanitization: There is no mention of sanitization or filtering of note content before processing or formatting.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:44 PM
Security Audit — agent-trust-hub — logseq-organization