linkedin-engagement

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill refers to an external Node.js package, @coldiq/mcp, to be fetched from the npm registry.
  • [COMMAND_EXECUTION]: Instructions are provided for the user to execute an npx command to initialize the vendor's MCP tool with an API key.
  • [PROMPT_INJECTION]: The skill is designed to ingest untrusted external data from LinkedIn posts and influencer profiles to generate outreach strategies.
  • Ingestion points: Data from mcp__coldiq__find_influencers and mcp__coldiq__extract_post_engagement.
  • Boundary markers: None present in the instructions.
  • Capability inventory: The skill generates text for DMs and comments but does not possess direct file-writing or subprocess execution capabilities in its own logic.
  • Sanitization: No explicit validation or filtering of external content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 06:37 PM
Security Audit — agent-trust-hub — linkedin-engagement