skills/unbrowse-ai/sites/afrinic/Gen Agent Trust Hub

afrinic

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration and documentation point to an external MCP server hosted at https://unbrowse.ai/mcp/afrinic.net.
  • [COMMAND_EXECUTION]: Documentation provides commands for setting up the MCP server using the claude and codex CLIs, and installing the skill via npx.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from afrinic.net, which is a potential surface for indirect prompt injection if the source content contains malicious instructions.
  • Ingestion points: Results from RDAP queries and readable text/links from afrinic.net pages.
  • Boundary markers: No specific delimiters are specified to separate fetched content from agent instructions.
  • Capability inventory: The skill allows network requests and browser interaction recording via the vendor proxy.
  • Sanitization: No explicit content sanitization or filtering is described in the skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 10:56 AM