copywriting
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely through natural language instructions and local markdown references. No suspicious patterns related to exfiltration, remote execution, or obfuscation were found.
- [NO_CODE]: There are no scripts (Python, JavaScript, shell) or executable files included in the skill. All logic is contained within markdown files.
- [EXTERNAL_DOWNLOADS]: No external network calls, downloads, or remote script executions are present.
- [DATA_EXFILTRATION]: The skill reads a local context file (
.claude/product-marketing-context.md) if available to improve its output, which is a standard practice for agent context and does not involve exfiltration. - [PROMPT_INJECTION]: The instructions are focused on copywriting principles and do not attempt to bypass safety filters or override system instructions.
Audit Metadata