note-titles-and-tags
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 analyze note content to generate organizational suggestions, which creates a potential surface for indirect prompt injection if note content contains malicious instructions.
- Ingestion points: The skill reads note titles and full body content provided by the user or retrieved from a connected notes application (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores potentially adversarial instructions embedded within the note data.
- Capability inventory: The skill possesses the capability to rename notes, modify tags, and move files within a connected notes environment.
- Sanitization: The instructions do not specify any validation or sanitization steps for the input data.
- Mitigation: The skill employs a strict "propose, then wait" policy (Step 9) that prevents any automated modifications without explicit user approval.
Audit Metadata