analyzing-customers
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, hardcoded credentials, or unauthorized network operations were detected. The skill is primarily instructional and provides templates for structured customer research.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to ingest and process untrusted data from external websites, such as customer reviews from G2, Capterra, and social media.
- Ingestion points: Review Mining and Social Listening methods (WebSearch) and user-provided CRM/support data.
- Boundary markers: None specified in the instructions to separate data from instructions.
- Capability inventory: The skill uses only analytical and search tools; it does not contain scripts, file-writing capabilities, or shell execution commands.
- Sanitization: No explicit sanitization or filtering of external content is mentioned. While the surface exists, the lack of dangerous system capabilities (RCE, file writes) ensures the risk is low and primarily limited to potential narrative manipulation in the final analysis report.
Audit Metadata