duckduckgo-search

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill implements a standard wrapper for a legitimate search utility and follows best practices for tool availability verification before execution.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting external data from the web. This is a known behavior of search-oriented skills and is considered safe within its intended use case.
  • Ingestion points: Search results including titles, snippets, and URLs fetched from DuckDuckGo via the ddgs CLI or Python library as described in SKILL.md.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or specific ignore-rules for the fetched search results.
  • Capability inventory: The skill uses terminal (shell commands) and execute_code (Python) to perform its functions.
  • Sanitization: Absent; search result content is processed directly from the service output without filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 07:07 AM