ai-data-engineering
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 includes code examples that pass API keys as literal parameters (e.g., voyage_api_key="your-api-key", openai_api_key="your-api-key"), which encourages embedding secret values directly into generated code/commands and thus requires the LLM to handle/output secrets verbatim.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests external web content and user-generated documents (e.g., "HTML | BeautifulSoupLoader — Web pages, wikis" in references/rag-architecture.md and loaders for PDFs/Markdown/chat logs) and then uses those retrieved chunks as context for RAG retrieval and LLM generation, meaning the agent will read and act on untrusted third‑party content.
Audit Metadata