notion-automation

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of documentation and configuration examples for Notion automation, focusing on legitimate data synchronization and workflow triggers across common office platforms.\n- [PROMPT_INJECTION]: The skill defines workflows that ingest untrusted data from external sources (e.g., Slack messages, form submissions, and GitHub issues), which presents an attack surface for indirect prompt injection. This is a characteristic of the skill's intended automation functionality.\n
  • Ingestion points: External content from forms, Slack, and GitHub issues defined in SKILL.md.\n
  • Boundary markers: Absent in the workflow configuration examples.\n
  • Capability inventory: Capabilities include writing to Notion databases, sending Slack messages, and generating emails.\n
  • Sanitization: No sanitization logic is provided in the templates to handle potentially malicious instructions within the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:46 PM
Security Audit — agent-trust-hub — notion-automation