workspace-init
Warn
Audited by Snyk on Mar 27, 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 import flow explicitly fetches and parses arbitrary URLs (see "Import from URL" in SKILL.md) and scripts/init-workspace.sh uses curl/wget to write remote content into WORKSPACE.md which the agent will parse and act on (e.g., create projects, clone repos), allowing untrusted third-party content to influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata