marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to an external GitHub repository (
github.com/coreyhaines31/marketingskills) that is not from a recognized trusted organization. The instructions suggest installing a "bundle" from this source, which introduces a dependency on unverified third-party content. - [INDIRECT_PROMPT_INJECTION]: As the skill is designed to analyze marketing copy and behavioral science in design, it will inherently process user-controlled input that could contain malicious instructions designed to manipulate the agent's behavior.
- Ingestion points: User-provided marketing hooks, copy, and framing descriptions (SKILL.md).
- Boundary markers: None; the skill does not specify markers to separate user data from instructions.
- Capability inventory: No scripts or execution tools are contained within this specific skill file, though it refers to external scripts.
- Sanitization: There are no instructions for the agent to sanitize or ignore instructions embedded within the marketing materials it analyzes.
Audit Metadata