skills/firecrawl/openclaw/notion/Gen Agent Trust Hub

notion

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill instructs users to store their Notion API key in a local configuration file at ~/.config/notion/api_key. This key is subsequently read and used to authenticate requests to the official Notion API (api.notion.com). This is a standard and expected credential management practice for API-integrated skills.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating a potential surface for indirect prompt injection.
  • Ingestion points: Reads page content and database entries through the Notion API (e.g., GET /v1/blocks/{page_id}/children and POST /v1/data_sources/{id}/query in SKILL.md).
  • Boundary markers: None identified in the provided instructions; the agent processes the retrieved content directly.
  • Capability inventory: The skill uses curl to interact with the Notion API and perform file system operations like mkdir, echo, and cat for configuration management (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the content retrieved from the Notion API is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — notion