linkup-workflow

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface where untrusted data from the web is used to influence agent decisions.
  • Ingestion points: Data enters the context via variables such as {company_website}, {topic}, and {attendees} defined across the workflow templates in the references/workflows/ directory.
  • Boundary markers: The workflow definitions do not include explicit delimiters or instructions to ignore potential commands embedded within retrieved web content.
  • Capability inventory: The skill utilizes linkup.search and linkup.research for automated web-based retrieval and synthesis.
  • Sanitization: No explicit sanitization or filtering of the retrieved web-scraped content is implemented before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:21 PM
Security Audit — agent-trust-hub — linkup-workflow