nansen-web-searcher

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill initiates the installation of the 'nansen-cli' package from the Node.js registry (npm). This is a standard dependency required for the search and fetch operations provided by the skill.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from web search results and external URLs which are subsequently processed by the agent.
  • Ingestion points: Search snippets and titles from 'nansen web search', and full web page content from 'nansen web fetch' as described in SKILL.md.
  • Boundary markers: Absent; the instructions do not define delimiters or control measures to isolate untrusted web content from the agent's core instruction set.
  • Capability inventory: The agent is authorized to execute commands within the 'nansen' CLI namespace via the 'Bash(nansen:*)' tool restriction.
  • Sanitization: No automated sanitization, filtering, or instruction-extraction prevention is specified for the retrieved web content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 09:15 PM
Security Audit — agent-trust-hub — nansen-web-searcher