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
Bashtool to perform Notion API operations (read, write, move) andWebFetchto 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