notion

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to perform API requests. The commands are correctly structured to use environment variables for authentication ($NOTION_API_KEY), which prevents hardcoding secrets and protects them from exposure in process lists or logs.
  • [PROMPT_INJECTION]: The skill's functionality involves reading data from external Notion sources (pages and databases as described in SKILL.md), creating a surface for indirect prompt injection. However, this is inherent to the primary purpose of the skill, and there are no findings of instructions intended to bypass safety guidelines or override agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 12:07 PM
Security Audit — agent-trust-hub — notion