claude-prompting
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill contains only Markdown documentation files (references/basics.md and references/xml-formatting.md) and does not include any scripts, executables, or configuration files that could be run on a system.
- [SAFE] (SAFE): The content is strictly educational, providing best practices for prompt engineering and XML-style formatting based on official Anthropic guidelines.
- [SAFE] (SAFE): No prompt injection, data exfiltration, or obfuscation patterns were detected in the provided documentation or examples.
- [SAFE] (SAFE): While the documentation describes how to ingest data (a surface for Indirect Prompt Injection), it does not implement any logic or tools that would create a vulnerability.
Audit Metadata