target-script
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing a framework for the agent to generate marketing copy based on user-provided parameters. It does not perform any sensitive operations.
- [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected in the instructions or test cases.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts. It references other internal skills (e.g., moai-core:ai-slop-reviewer) for output refinement, which is standard behavior for modular agent ecosystems.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data (target audience profiles and product descriptions) and interpolates them into a 5-step generation pipeline. While it lacks explicit instruction-boundary markers for this input, the skill has no dangerous capabilities such as file system writes, shell access, or outbound network calls, rendering the injection surface benign.
- [OBFUSCATION]: A scan for Base64 encoding, zero-width characters, and other obfuscation techniques yielded no results.
Audit Metadata