skills/craftos-dev/craftbot/notion/Gen Agent Trust Hub

notion

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to perform API calls for managing Notion data structures.
  • [DATA_EXFILTRATION]: The instructions guide the retrieval of an API key from ~/.config/notion/api_key. This credential is used exclusively for authentication with the official Notion API service.
  • [PROMPT_INJECTION]: The skill creates an ingestion surface for untrusted data via Notion API responses.
  • Ingestion points: Notion API endpoints for pages, blocks, and databases.
  • Boundary markers: None present in the command examples.
  • Capability inventory: Shell command execution via curl.
  • Sanitization: No explicit sanitization or filtering of API responses is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 05:35 PM
Security Audit — agent-trust-hub — notion