nansen-web-searcher
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from web search results and web page fetching, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Web search results (organic snippets, knowledge graph) and specific URL content fetched via
nansen web searchandnansen web fetchmentioned in SKILL.md. - Boundary markers: No explicit delimiters or boundary markers are defined to separate untrusted web content from agent instructions.
- Capability inventory: The skill is restricted to using the
nansenCLI tool as defined in theallowed-toolsfield. - Sanitization: There is no evidence of content sanitization or instruction filtering for the data returned from external web sources.
Audit Metadata