gtm-meeting-prep

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from CRM activity logs, emails, and notes, which could contain adversarial content intended to influence agent behavior.
  • Ingestion points: CRM account records, opportunity stages, and activity history including email content from file searches and CRM tools.
  • Boundary markers: No specific delimiters or safety instructions are defined to isolate untrusted content within the instructions.
  • Capability inventory: The skill can read local profile files and generate PDF, HTML, and Markdown reports.
  • Sanitization: There is no mention of sanitizing or escaping the data retrieved from the CRM before processing.
  • [DYNAMIC_EXECUTION]: The skill provides an option to generate PDF reports using Python and the 'reportlab' library.
  • Description: Generating a PDF report involves dynamic script creation and execution, incorporating external data points from the CRM and local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:19 PM
Security Audit — agent-trust-hub — gtm-meeting-prep