daily-note
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read "yesterday's note" and carry over content, which creates an attack surface for indirect prompt injection. 1. Ingestion points: Data from previous notes and current user input are processed (SKILL.md). 2. Boundary markers: The instructions lack delimiters or constraints to prevent the agent from following instructions embedded within the ingested data. 3. Capability inventory: The skill is designed to interact with note-taking tools and connectors to create or append content to files (SKILL.md). 4. Sanitization: There is no requirement for the agent to sanitize or escape the content carried over from previous notes.
Audit Metadata