linkedin-campaign-complete

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted LinkedIn data through MCP tools, creating a surface for indirect prompt injection. Ingestion points: mcp__coldiq__enrich_person, mcp__coldiq__find_signals, mcp__coldiq__extract_post_engagement, and mcp__coldiq__fetch_page_content. Boundary markers: No delimiters are specified to isolate external data from instructions. Capability inventory: Tool calls for fetching live profile, post, and company page data. Sanitization: No content filtering or validation is mentioned for the retrieved data.
  • [REMOTE_CODE_EXECUTION]: The skill instructs the user to execute npx -y @coldiq/mcp@latest, which downloads and runs the vendor's package from the npm registry.
  • [EXTERNAL_DOWNLOADS]: The skill recommends downloading the @coldiq/mcp package from the npm registry, which is a well-known service.
  • [COMMAND_EXECUTION]: Provides a shell command to set an environment variable and run the MCP client as part of the setup process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 05:22 AM
Security Audit — agent-trust-hub — linkedin-campaign-complete