copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for the agent. It does not perform any sensitive operations, access local files, or request network permissions.
- [NO_CODE]: There are no scripts, binaries, or configuration files that execute code or manage dependencies within this skill.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided information (product details, audience data, and existing copy). While this constitutes an attack surface for indirect prompt injection, the skill possesses no operational capabilities—such as file writing, network requests, or command execution—that could be exploited by malicious input. The risk remains negligible as the output is confined to text generation.
Audit Metadata