interactive-writing-assistant

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data from local folders and voice transcripts, creating a surface for potential indirect prompt injection.
  • Ingestion points: The skill is instructed to search for and read content from user-defined 'Journal', 'Reading/Articles', and 'Topics' folders, as well as process voice-based user input (VUI).
  • Boundary markers: Instructions suggest using markdown blockquotes (>) to distinguish knowledge base findings and delimiters (%%) for comments, which provide basic visual separation but are not robust security boundaries.
  • Capability inventory: The agent has access to 'Read', 'Write', 'Edit', 'Glob', and 'Grep' tools, allowing it to modify the local file system.
  • Sanitization: The instructions do not specify any validation or sanitization of content retrieved from the knowledge base before it is integrated into the active document.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 02:49 PM