create-agent-skills

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: 0.80). The skill's generation_protocol (step_0 research_trigger) and README explicitly instruct the agent to use WebSearch / Context7 MCP to fetch current API/library documentation and web resources, meaning the agent will ingest and interpret arbitrary public third‑party web content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:03 PM