xhs-diagnosis
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied note titles and content, which are interpolated into agent prompts. This presents a surface for potential indirect prompt injection attacks where malicious instructions could be embedded in the analyzed text.
- Ingestion points: Note content fields (
title,content,category) are extracted from user input as defined inSKILL.md. - Boundary markers: The prompts located in the
references/prompts/directory do not employ explicit delimiters or boundary markers to isolate user-provided data from the system instructions. - Capability inventory: The skill is restricted to text analysis and generation; it has no access to the file system, network operations, or command-line execution.
- Sanitization: No input sanitization or filtering logic is present to handle potentially malicious instructions within the user-provided note content.
Audit Metadata