sales-coaching

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it analyzes untrusted data from prospect replies and call transcripts.
  • Ingestion points: Ingests external email text and meeting transcripts (SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded prompts are provided.
  • Capability inventory: Features data analysis, reporting, and content generation.
  • Sanitization: Lacks specific sanitization procedures for ingested external content.
  • [DATA_EXFILTRATION]: The skill requires access to sensitive business environments (CRMs, email tools). This access is necessary for the skill's primary function and targets well-known services like Salesforce, HubSpot, and Gong.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 10:18 PM