notes-to-draft
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 untrusted user-supplied data in the form of messy notes to generate a draft.
- Ingestion points: In the 'What to ask for' section, the skill explicitly instructs the agent to request 'The notes. All of them, as messy as they are' from the user.
- Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore or delimit instructions that may be embedded within the user-provided notes.
- Capability inventory: The skill is capable of generating structured Markdown output and suggests using tool connectors, such as a 'Scratchpad connector', to save content to external note-taking applications.
- Sanitization: There are no instructions provided to sanitize, escape, or validate the content of the notes before they are incorporated into the drafting process.
Audit Metadata