linkup-fetch

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were identified. The skill implements documented functionality for interacting with the Linkup API.
  • [DATA_EXFILTRATION]: Network requests are directed to the vendor's official API domain (api.linkup.so). Authentication is handled via a placeholder variable ($LINKUP_API_KEY), which is consistent with secure credential management practices.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites, creating a potential surface for indirect prompt injection. \n
  • Ingestion points: Untrusted content is retrieved from arbitrary URLs using the fetch API defined in SKILL.md. \n
  • Boundary markers: Instructions in SKILL.md guide the agent to extract only necessary information, reducing the likelihood of processing malicious instructions embedded in fetched pages. \n
  • Capability inventory: Network access is required to communicate with the Linkup API service. \n
  • Sanitization: There are no specific instructions for sanitizing or escaping the fetched content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:32 AM
Security Audit — agent-trust-hub — linkup-fetch