notion

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes curl commands to interact with the well-known Notion API service (api.notion.com). This is the intended primary purpose of the skill and uses standard API interaction patterns.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) by ingesting untrusted data from an external source.
  • Ingestion points: External content such as Notion page blocks, search results, and database records are retrieved via the /v1/blocks, /v1/search, and /v1/data_sources endpoints in SKILL.md.
  • Boundary markers: No delimiters or explicit instructions are provided to help the agent differentiate between its own instructions and potentially malicious content retrieved from the Notion API.
  • Capability inventory: The skill utilizes shell execution for curl commands and reads a specific local file (~/.config/notion/api_key) for credentials.
  • Sanitization: No sanitization, filtering, or validation is applied to data retrieved from the Notion API before it enters the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:45 PM
Security Audit — agent-trust-hub — notion