Sales

Fail

Audited by Snyk on Mar 5, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The prompt includes a mandatory "Voice Notification" that requires executing a curl POST and performing side-effectful actions immediately upon invocation, which is an out-of-scope, non-advertised instruction unrelated to the Sales skill's stated content-generation purpose.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and processes a "URL to product page" as required input (see Workflows/CreateNarrative.md Step 1 and CreateSalesPackage Step 1), so the agent will fetch and interpret public third‑party web content that can materially influence downstream narrative, visual prompts, and tool invocations, enabling indirect prompt injection.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 5, 2026, 07:39 AM