spring-refresh

Warn

Audited by Snyk on Apr 26, 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 "refresh" workflow (SKILL.md Mode: refresh) instructs invoking the core:deep-research tool to refresh local research docs — and EXAMPLES.md and TROUBLESHOOTING.md explicitly state deep-research may use EXA web search / WebFetch / WebSearch to pull public web content (e.g., GitHub and web pages), which the agent then reads and uses to decide updates, so untrusted third‑party content can influence its actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 26, 2026, 10:56 AM
Issues
1