prompt-engineering
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely documentation-based, providing templates and instructions on how to write effective prompts for large language models. No malicious patterns, data exfiltration attempts, or unauthorized behaviors were detected.
- [NO_CODE]: No executable scripts, shell commands, or automation logic are present. The content consists of markdown text for human or agent reference.
- [INDIRECT_PROMPT_INJECTION]: While the skill documents templates that interpolate user input (e.g.,
{user_query}), it specifically warns against prompt injection in its 'Anti-Patterns' section and recommends the use of delimiters as a security best practice. The skill itself possesses no capabilities (tools, network, or file access) that could be exploited through these templates.
Audit Metadata