action-items
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text (meeting transcripts, email threads, chat logs) and has the capability to write output to external notes applications.
- Ingestion points: Processes any amount of text provided by the user for task extraction.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or provide the agent with "ignore embedded instructions" warnings for the source text.
- Capability inventory: Offers to save results to connected notes apps (e.g., via the "Scratchpad connector"), potentially creating new notes or appending to existing ones.
- Sanitization: Absent. There are no instructions for sanitizing or escaping the content extracted from the untrusted source text before saving it to a notes application.
Audit Metadata