ddgr
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'ddgr' CLI tool for local execution of web searches.
- [EXTERNAL_DOWNLOADS]: The skill initiates network requests to retrieve results from DuckDuckGo. This is considered a standard and safe operation for a search tool targeting a well-known service.
- [PROMPT_INJECTION]: The skill provides an indirect prompt injection surface by processing content from web search results.
- Ingestion points: Data enters the context from search result snippets and URLs via 'ddgr' (SKILL.md, recipes.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation.
- Capability inventory: The skill uses local command execution ('ddgr') and suggests interaction with browser tools like 'playwright-cli'.
- Sanitization: No specific content sanitization or validation of the search results is described.
Audit Metadata