copywriting
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious patterns were identified in the instructional content. The skill follows best practices for providing structured guidance to an AI agent.
- [DATA_EXPOSURE] (LOW): The skill attempts to read a local file at
.claude/product-marketing-context.md. This is a domain-specific context file and does not match the criteria for sensitive system credentials or private keys. - [NO_CODE] (SAFE): The skill consists entirely of Markdown files and does not include Python scripts, Node.js packages, or shell commands, which significantly reduces the attack surface for RCE or persistence.
- [INDIRECT_PROMPT_INJECTION] (LOW): As a writing tool, the skill processes user-provided input. While it lacks explicit sanitization instructions, it also lacks any dangerous capabilities (network, file writes, or command execution) that could be exploited via an indirect injection attack.
Audit Metadata