news-to-note

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by fetching untrusted news content and processing it alongside private user notes to generate insights. This is a common pattern for such tools and is mitigated by the agent's internal safety guardrails.
  • Ingestion points: Untrusted news content fetched via WebFetch and WebSearch as defined in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded directives within the fetched news content.
  • Capability inventory: The skill can search (search_notes), read (read_note), and create/edit (create_note, edit_block) user notes.
  • Sanitization: Content cleaning is mentioned for usability (removing ads/navigation) but does not specifically filter for malicious instructions.
  • [SAFE]: The skill uses tools and identifiers (wpsnote) consistent with its stated purpose and the author's identity, representing standard vendor-owned resource usage.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 11:13 AM