paw-mkt-psychology
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes instructions in
references/shared-patterns.mdto install theagent-browsertool from the official GitHub repository of Vercel Labs, which is a trusted organization. This facilitates web-based marketing research activities. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external inputs such as brand guidelines, customer feedback, and website content. While this creates a surface for indirect prompt injection, the risk is inherent to the primary function of the tool. The skill defines specific response protocols and an ethical verification gate to mitigate risks associated with untrusted data ingestion. Ingestion points: Loading brand context, positioning data, and auditing live URLs. Capability inventory: File system write access for saving deliverables and browser automation via external tools. Sanitization: The 'Ethical Verification Gate' provides a checklist to ensure tactical recommendations are transparent and non-manipulative.
Audit Metadata