AGENT LAB: SKILLS

spec-driven-planning

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to use WebSearch/WebFetch and bash/curl to fetch competitor product documentation, external API docs, and web research (open/public URLs), so the agent will ingest untrusted third-party web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:23 AM