sales-call-prep
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs research tasks as described in its metadata. It interacts with CRM and outreach tools (e.g., Salesforce, HubSpot, SmartLead) to reconstruct customer interaction timelines, which is its primary functional goal. No unauthorized data exfiltration or credential theft patterns were detected.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from external sources during its research phase.
- Ingestion points: Web search results, LinkedIn profiles, and external company websites retrieved during the 'Company Deep Dive' and 'Person Deep Dive' steps.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the gathered data.
- Capability inventory: The skill utilizes
web-search,contact-finding, anddata-analysistools. It does not have access to command-line execution or file-system writing outside of its own configuration path. - Sanitization: No explicit sanitization or filtering of external content is specified before the data is used to generate the call brief.
Audit Metadata