tidy-up-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (notes) and has the capability to write to external note-taking applications (e.g., the Scratchpad connector). While this presents a vulnerability surface, the skill includes strong mitigation measures.
- Ingestion points: Processes user-supplied text or content retrieved from connected note-taking apps.
- Boundary markers: Utilizes an 'Inventory first' step to define the scope of content before processing and a 'Report the changes' step to differentiate between user content and AI-generated formatting.
- Capability inventory: Capable of writing new notes or updating existing ones via external tools (file-write/tool-call capability).
- Sanitization: Relies on human-in-the-loop verification via a mandatory change report and explicit confirmation before any destructive actions (deletions) are performed.
Audit Metadata