sbox

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's required retrieval workflow explicitly fetches documentation and API signatures from the public site https://sdocs.suiram.dev (via /api/sbox/search, /api/sdk/describe, /api/sdk/get-signature, etc.), meaning the agent reads and acts on third-party web content that can materially influence its code-generation decisions and thus could carry indirect prompt-injection risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires runtime calls to https://sdocs.suiram.dev (e.g., /api/sbox/search, /api/sdk/describe) to fetch API signatures and documentation that are injected into the agent's context and directly control its prompts/instructions, making that URL a required external dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 06:34 PM