notion

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill facilitates access to a sensitive API key stored in ~/.config/notion/api_key. Although the key is sent to the official Notion API domain (api.notion.com), reading credentials from the filesystem is a sensitive operation.
  • [COMMAND_EXECUTION]: The skill instructions involve executing shell commands such as mkdir, echo, cat, and curl to manage configuration and perform API requests.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its data processing workflow.
  • Ingestion points: The skill retrieves content from external Notion pages, blocks, and databases via API calls.
  • Boundary markers: The instructions do not include markers to separate untrusted data or warn the agent about potential embedded instructions within that data.
  • Capability inventory: The skill can modify Notion data through various write operations (POST, PATCH) using curl.
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from the API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 09:12 PM