create-database-row

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied natural language to extract database properties.
  • Ingestion points: Natural language requests containing property values (SKILL.md).
  • Boundary markers: The instructions do not specify boundary markers or delimiters for isolating user-provided data.
  • Capability inventory: The skill uses the Notion MCP server to perform database write operations.
  • Sanitization: No sanitization or escaping of external content is specified before database insertion.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:43 AM
Security Audit — agent-trust-hub — create-database-row