pica-claude-agents

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill runs an external MCP server at runtime via "npx @picahq/mcp", which executes remote package code and exposes tools that the agent will invoke (so the @picahq/mcp invocation is a required, runtime-executed external dependency that can control agent behavior).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 01:11 AM