foundations-consumer-neuroscience
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, playbooks, and reference materials. No executable scripts, binary files, or automated shell commands are present.
- [SAFE]: All external URLs and source citations point to established academic journals, scientific repositories, and government domains such as nature.com, jstor.org, and legislation.gov.uk. No evidence of typosquatting or malicious redirects was found.
- [SAFE]: The skill includes extensive 'Misuse Boundary' sections and an 'Ethics Operational Checklist' designed to prevent the exploitation of pre-conscious neural mechanisms and ensure compliance with UK, EU, and US regulatory standards.
- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows for processing untrusted user data, such as qualitative feedback and NPS verbatims. While this creates a theoretical attack surface for indirect prompt injection, the skill implements strict 'Harm Test' protocols and boundary markers to mitigate these risks.
Audit Metadata