duckduckgo-search
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval and processing of untrusted data from the web, creating a potential attack surface.
- Ingestion points: Data is ingested via
DDGS.text(),DDGS.news(), andDDGS.images()methods, which fetch snippets, titles, and body content from external websites (SKILL.md). - Boundary markers: There are no instructions provided to the agent regarding the use of delimiters or specific prompts to ignore instructions that might be embedded in the search results.
- Capability inventory: The skill does not define any direct dangerous capabilities like file writing or network exfiltration; however, the agent's general capabilities may be targeted by injected instructions.
- Sanitization: No sanitization or escaping mechanisms for the retrieved web content are mentioned in the implementation examples.
Audit Metadata