customer-research
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and reference templates. No malicious code, hidden commands, or obfuscated content were detected.
- [DATA_EXFILTRATION]: While the skill references a local context file (
.agents/marketing-context.md), it does not perform any network requests, access sensitive system directories, or attempt to harvest credentials. - [PROMPT_INJECTION]: The instructions establish a professional persona and enforce high-quality research standards (Jobs-to-be-Done, Ehrenberg-Bass). There are no attempts to bypass safety filters, extract system prompts, or override agent constraints.
- [REMOTE_CODE_EXECUTION]: The skill does not contain any scripts, package dependencies, or commands to download and execute remote content.
- [NO_CODE]: The skill is strictly instructional and does not provide any software, scripts, or binary files.
Audit Metadata