customer-research
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of markdown-based instructions and configuration files without any executable scripts, binaries, or command-line operations.
- [PROMPT_INJECTION]: Analysis of the instructions shows no attempts to override agent safety protocols, extract system prompts, or utilize jailbreak-style 'DAN' patterns.
- [DATA_EXPOSURE]: The skill references standard project context files (e.g., product-marketing-context.md) to tailor its research, which is a legitimate and safe use of local project information.
- [INDIRECT_PROMPT_INJECTION]: Although the skill processes untrusted external data such as forum posts and reviews, the risk is negligible as the instructions focus on signal extraction and synthesis rather than execution of content found in that data.
Audit Metadata