ethical-persuasion-design
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown instructions, workflows, and evaluation prompts. It does not include any executable scripts, binary files, or configuration that enables network or file system access.
- [SAFE]: No prompt injection attempts, obfuscation techniques, or hidden instructions were detected in the skill metadata or body.
- [SAFE]: The skill does not define or use any external dependencies or remote code patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided marketing copy for auditing. While this presents an ingestion surface for untrusted data, the skill lacks any capabilities (such as shell execution or network requests) that could be exploited via indirect injection.
Audit Metadata