linkup-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a workflow where user-supplied inputs and external web data are interpolated into prompts for tool calls, creating an indirect prompt injection surface.\n
- Ingestion points: Untrusted data enters the agent context via user-provided variables such as
{company_website},{company_name},{ideal_customer_profile}, and{target_accounts}across multiple workflow files, includingaccount_enrichment.mdandicp_to_lead_list.md.\n - Boundary markers: The skill does not define explicit delimiters or 'ignore embedded instructions' warnings for the data being processed.\n
- Capability inventory: The skill utilizes the
linkup.search,linkup.research, andlinkup.extracttool capabilities to retrieve and process web content.\n - Sanitization: No evidence of input validation, content escaping, or filtering was found in the instructional files.
Audit Metadata