sales-smartlead

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt explicitly documents API key authentication via an api_key query parameter and example API usage, which encourages embedding secrets verbatim in requests/commands (e.g., curl or code samples), creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly says SmartAgents "point to data sources (LinkedIn, company website, news)" and research each prospect, which means the agent ingests untrusted public web/social content that can change generated messaging and actions.