spec-context

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill requires querying the Linear MCP endpoint (https://mcp.linear.app/mcp) at runtime to fetch spec issue bodies which are injected into the agent's context and therefore directly influence/drive prompts, making it a required external dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 03:53 AM