flow-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for a specific note-taking methodology. Analysis confirms that the content is strictly instructional and does not include any unauthorized commands, network operations, or sensitive data access.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by processing external content provided by users. While this is an attack surface, it is necessary for the skill's primary function and carries minimal risk.
- Ingestion points: Material provided by the user, such as notes, readings, or transcripts (SKILL.md).
- Boundary markers: None specified for input content.
- Capability inventory: Output of text, Mermaid diagram generation, and optional integration with note-saving tools (e.g., Scratchpad connector).
- Sanitization: No explicit validation or filtering logic for processed text.
Audit Metadata