outline-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted text which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill accepts transcripts, notes, slides, and chapters provided by the user (as described in the "How to do it" section of SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or specific warnings to the agent to disregard instructions found within the source material.
- Capability inventory: The skill has the ability to interface with external note-taking applications (such as the Scratchpad connector) to save the generated content.
- Sanitization: There is no description of content sanitization, filtering, or validation for the input text.
Audit Metadata