nby-notion-reading-notes

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from external articles to generate summaries.\n
  • Ingestion points: Round 2 fetches article content from Notion pages via the API, and Round 2.5 fetches external web content using Jina WebFetch (r.jina.ai).\n
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the fetched article content.\n
  • Capability inventory: The skill utilizes the Bash tool to perform Notion API operations (read, write, move) and WebFetch to retrieve web content.\n
  • Sanitization: No logic for sanitizing or filtering external content is defined before the data is passed to the analysis and generation phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 08:41 AM