abm-engagement-scoring
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a measurement framework that ingests untrusted external data (website visits, email interactions, LinkedIn engagement) to calculate engagement scores. Ingestion points: External website logs, email tracking platforms, and CRM records described in the measurement model. Boundary markers: No specific delimiters or safety instructions are defined to prevent the agent from being influenced by data within these signals. Capability inventory: The skill instructs the agent to trigger CRM opportunity creation and sales alerts based on score thresholds. Sanitization: No validation or sanitization logic is specified for the incoming signal data.
Audit Metadata