linkup-search

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or safety bypass attempts were detected. The skill focuses on providing legitimate technical guidance for API usage.
  • [EXTERNAL_DOWNLOADS]: References official vendor resources, including an MCP server endpoint at linkup.so and a GitHub repository under the LinkupPlatform organization.
  • [COMMAND_EXECUTION]: Includes standard configuration commands for CLI tools to set up the MCP integration.
  • [PROMPT_INJECTION]: As a search tool, the skill creates a surface for indirect prompt injection from web data. • Ingestion points: Web content retrieved via linkup-search and linkup-fetch tools. • Boundary markers: Absent; instructions do not mandate delimiters for retrieved content. • Capability inventory: Tools for web searching and content extraction. • Sanitization: No specific filtering or sanitization logic is provided in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 03:21 PM