copywriting
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- SAFE (SAFE): The skill contains no malicious patterns. It is strictly limited to providing natural language instructions and frameworks for copywriting tasks.
- NO_CODE (LOW): This is a 'no-code' skill. It does not include any scripts (Python, JS, Bash), configuration files for package managers, or commands that interact with the host system.
- PROMPT_INJECTION (SAFE): No instructions were found that attempt to override system prompts, bypass safety filters, or extract underlying configurations.
- DATA_EXFILTRATION (SAFE): There are no network-capable commands (curl, wget) or references to sensitive local files (~/.ssh, .env) that could lead to data exposure.
- INDIRECT_PROMPT_INJECTION (LOW): While the skill processes user-provided inputs (target audience, product descriptions), it has no 'write' or 'execute' capabilities. The risk is limited to influencing the tone and content of the generated text within the agent session.
Audit Metadata