para-organizer

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided data in the form of note titles and folder structures, creating a potential attack surface where instructions embedded in those strings could attempt to influence the agent's behavior.
  • Ingestion points: Note titles and folder names are retrieved from the user's connected note-taking application or provided as text input.
  • Boundary markers: The instructions do not specify the use of delimiters or explicit directives to ignore instructions that might be contained within note titles or folder names.
  • Capability inventory: The skill has the capability to list files/folders and perform move, rename, or creation operations via connected tools (e.g., the Scratchpad connector).
  • Sanitization: The skill lacks explicit instructions for the agent to sanitize or validate the content of retrieved note titles before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 12:07 AM