competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): The skill specifies reading a local context file (.claude/product-marketing-context.md) for domain information. This is a legitimate use of local context and does not involve accessing sensitive system credentials or exfiltrating data.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external packages or remote scripts are downloaded or executed. The skill is entirely composed of markdown instructions and templates.
- [Prompt Injection] (SAFE): The instructions set a professional persona for content creation and do not attempt to override the underlying model's safety protocols or extract system prompts.
- [Indirect Prompt Injection] (SAFE): Although the skill processes external context, it does not possess any dangerous capabilities (like shell access or network connectivity) that could be triggered by malicious instructions in the context file.
Audit Metadata