list-building-prospeo

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves B2B lead data and company intelligence from api.coldiq.com and mcp.prospeo.io.
  • [REMOTE_CODE_EXECUTION]: Users are instructed to run the @coldiq/mcp package using npx to facilitate service integration; the package is maintained by the skill author.
  • [INDIRECT_PROMPT_INJECTION]: The beginner workflow ingests website content to generate summaries and perform business classification via LLM prompts.
  • Ingestion points: resources/templates/beginner-workflow.md.
  • Boundary markers: The prompts do not use specific delimiters to isolate external data.
  • Capability inventory: The skill uses search and enrichment tools but does not have direct command execution capabilities on the ingested data.
  • Sanitization: No sanitization is performed on the scraped content before LLM processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 08:56 AM
Security Audit — agent-trust-hub — list-building-prospeo