marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text and a catalog of psychological mental models. No malicious patterns, obfuscation, or dangerous commands were detected.
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided marketing assets, which creates a surface for indirect prompt injection. However, as the skill possesses no dangerous capabilities (e.g., shell access, network operations, or file system modification), this represents a negligible risk. * Ingestion points: User-provided marketing assets (landing pages, email sequences, and marketing campaign assets referenced in SKILL.md). * Boundary markers: Not present. * Capability inventory: Limited to textual analysis and the generation of marketing recommendations. * Sanitization: No explicit sanitization of external assets is performed.
Audit Metadata