hoekee-com-sg

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to a remote Model Context Protocol (MCP) server at https://unbrowse.ai/mcp/hoekee.com.sg to execute its tools. This is the primary infrastructure for the skill's functionality as provided by the developer.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge to external web content from hoekee.com.sg, which represents a surface for indirect prompt injection if the fetched content contains malicious instructions.
  • Ingestion points: Tools hoekee_com_sg__get_search and hoekee_com_sg__read_page in SKILL.md ingest external data from the web.
  • Boundary markers: None explicitly defined in the tool output instructions.
  • Capability inventory: Provides capabilities to search, read, and follow links on the targeted domain.
  • Sanitization: No specific sanitization or filtering of the external content is described before it is passed to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 10:55 AM