content-copywriting
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides copywriting assistance following marketing frameworks like AIDA and PAS, while incorporating legal compliance checks for Korean advertising laws.
- [PROMPT_INJECTION]: The skill interpolates user-supplied product information into its copywriting workflows. While it lacks explicit boundary markers to delimit this external data, the skill's available toolset does not include high-risk capabilities like network access or file system persistence, restricting any potential indirect prompt injection to the generated text.
- [COMMAND_EXECUTION]: Documentation files references an internal Python script (humanize_html.py) and provide CLI examples. These instructions are intended for the agent to process its own generated output using internal skill components, which is a standard functional behavior for the vendor's humanization workflow.
Audit Metadata