find-contacts

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied criteria such as job titles, company names, and seniority levels to perform contact discovery tasks. This ingestion of untrusted data creates a surface for indirect prompt injection. • Ingestion points: User-provided search parameters used in Sales Navigator and MCP tool calls. • Boundary markers: No specific delimiters or boundary markers are defined in the instructions to isolate user input. • Capability inventory: The skill interacts with the file system through reference reading and executes professional enrichment via mcp__coldiq__find_people and mcp__coldiq__enrich_person tools. • Sanitization: There are no explicit instructions for validating or sanitizing user-provided search terms.
  • [EXTERNAL_DOWNLOADS]: The skill references the @coldiq/mcp Node.js package and the api.coldiq.com endpoint, which are official resources provided by the skill author for lead generation and enrichment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 08:56 AM