duckducksearch

Fail

Audited by Snyk on Mar 5, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The prompt includes examples that embed credentials directly in proxy URLs and environment variables (e.g., "socks5://user:password@host:port"), which encourages including secret values verbatim in code/commands and therefore risks exposing secrets through the LLM output.

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md shows the skill uses the duckduckgo-search DDGS APIs (e.g., Core Functionality "text"/"news"/"images" examples) and returns open-web fields like "href" and "body" (see Result Format), so it fetches and ingests untrusted public web content that could influence agent actions.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 5, 2026, 07:54 AM