ai-sdr-agent
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires collecting the user's LiveAvatar API key and instructs the agent to embed that exact key verbatim into generated shell commands and a .env.local file (and examples show the raw key), which forces the LLM to handle and output secrets directly.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill requires the user to supply a Website URL (and even notes "Website unreachable
- Can't fetch the URL") and uses NEXT_PUBLIC_WEBSITE_URL to auto-start, indicating it will fetch and use arbitrary public website content provided by users, which is untrusted third-party content the agent will read and interpret.
Audit Metadata