skill-factory

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: 0.90). The skill's /meta-claude:skill:research command explicitly uses the Firecrawl API to perform automated web scraping of public or user-specified sources (arbitrary URLs/public websites) and then ingests and processes that research as part of the workflow, exposing the agent to untrusted, user-generated third‑party content and enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:01 PM