boxing-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a purely instructional guide for text formatting. It provides a structured methodology for organizing notes into Markdown sections and offers best practices for labeling and summarizing content. No suspicious commands, obfuscation, or unauthorized access patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data (user-provided notes) and format them. While this represents a potential surface for indirect prompt injection if the source material contains hidden instructions, the skill does not have dangerous capabilities that could be exploited.
- Ingestion points: User-supplied notes or source material provided in response to the skill's prompts (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters to wrap the untrusted input text.
- Capability inventory: No network operations, arbitrary command execution, or local file system writes are present. The skill only offers to save notes via a connected note-taking tool (e.g., Scratchpad connector) or provide Markdown output.
- Sanitization: The skill does not implement specific sanitization or filtering of the input text.
Audit Metadata