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

apnic

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a proxy for apnic.net via the Unbrowse MCP service, allowing agents to query WHOIS records and read page content.
  • [INDIRECT_PROMPT_INJECTION]: The apnic_net__read_page tool ingests external content from apnic.net. While this is a surface for indirect instructions, the skill limits the scope to the apnic.net domain and provides structured instructions for the agent to report only succeeded results, which is a standard pattern for web-enabled skills.
  • [CREDENTIALS_UNSAFE]: The documentation correctly instructs users to store API keys in a secret manager rather than committing them to configuration files, demonstrating alignment with security best practices.
  • [EXTERNAL_DOWNLOADS]: The skill references its own MCP service endpoints (unbrowse.ai) for functionality, which is consistent with its stated purpose and the author's identity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 10:55 AM