customer-research
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and research frameworks. It does not include any scripts, binaries, or automated tasks that could compromise a system.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions ask the agent to process external data like customer transcripts and online reviews. While this exposes the agent to untrusted data, the skill lacks the capabilities to perform high-risk actions based on that data, and the instructions focus solely on analysis and synthesis. This is a low-risk architectural feature inherent to research agents.
Audit Metadata