sales-coach

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to facilitate the review of external sales data, including call recordings and transcripts. This functionality introduces a surface for indirect prompt injection, where an attacker could embed instructions in a transcript to manipulate the agent's behavior during coaching.\n
  • Ingestion points: The skill instructions specifically direct the agent to review external call transcripts, performance data, and pipeline health metrics (SKILL.md).\n
  • Boundary markers: No specific delimiters or safety instructions are provided to ensure the agent ignores instructions potentially embedded within the analyzed data.\n
  • Capability inventory: The skill operates within an environment that provides shell and script execution capabilities via the included run.sh wrapper.\n
  • Sanitization: There are no defined procedures for validating or sanitizing the external text inputs before they are processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 10:49 PM