notion-workflow-sync

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to process data from external business systems, which can serve as a vector for indirect instructions. \n
  • Ingestion points: Data retrieved from Odoo and BIR systems (SKILL.md). \n
  • Boundary markers: No delimiters or instructions to ignore embedded commands are specified in the documentation. \n
  • Capability inventory: The skill includes instructions for writing to Notion databases via the notion tool. \n
  • Sanitization: There is no mention of sanitization or structural validation for the external data ingested.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 10:43 AM
Security Audit — agent-trust-hub — notion-workflow-sync