product-jtbd-copy
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides static instructions for copywriting and does not include any executable code, scripts, or remote dependencies.
- [PROMPT_INJECTION]: No evidence of prompt injection, role-play bypasses, or instructions to disregard safety guidelines were detected.
- [DATA_EXFILTRATION]: No network operations (such as curl or fetch) or access to sensitive file paths (such as credentials or environment files) are present.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the
$ARGUMENTSvariable. However, it lacks dangerous capabilities—such as file writing, command execution, or network access—needed to transform an injection into a security threat. The risk is limited to content manipulation within the text output.
Audit Metadata