linkup-search

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation refers to the installation of official SDKs (linkup-sdk) via standard package managers (pip, npm). These are vendor-provided resources from 'linkupplatform' intended for API integration.
  • [INDIRECT_PROMPT_INJECTION]: As a web search and scraping skill, it inherently processes untrusted data from external websites.
  • Ingestion points: Web search results, snippets, and full page content retrieved from the Linkup Search API (documented in SKILL.md and references/LINKUP_API_REFERENCE.md).
  • Boundary markers: The instructions focus on query construction and retrieval planning but do not explicitly mandate the use of delimiters or boundary markers to separate retrieved web content from the agent's internal reasoning.
  • Capability inventory: The skill utilizes the linkup-search MCP tool and network requests to api.linkup.so. It does not contain scripts for local file manipulation or arbitrary code execution.
  • Sanitization: No specific data sanitization or filtering logic is provided for the content returned by the search API; the agent is expected to synthesize results as needed.
  • [DATA_EXFILTRATION]: The skill uses the LINKUP_API_KEY for authentication to the vendor's own API. This follows standard security practices for managing API credentials via environment variables and does not represent an exfiltration risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 08:10 AM
Security Audit — agent-trust-hub — linkup-search