langchain-aws

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly documents an "Option 3: Explicit credentials" pattern (aws_access_key_id, aws_secret_access_key, aws_session_token passed as string arguments), which encourages embedding secret values verbatim in code/requests and thus poses a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill includes a BrowserToolkit workflow (SKILL.md example using create_browser_toolkit and "Go to langchain.com and summarize the homepage") which has the agent fetch and read public third‑party web pages, meaning untrusted web content can be ingested and influence agent actions.