openspec-apply-change

Warn

Audited by Snyk on Aug 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). SKILL.md runtime path reads apply instructions (openspec instructions apply ... --json), then reads arbitrary contextFiles from that output and treats the resulting CLI-provided context/operationGuidance as prompt-level inputs, so outsider-authored content submitted into the OpenSpec change/repo can be ingested without selecting a specific item.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 20, 2026, 10:25 AM
Issues
1
Security Audit — snyk — openspec-apply-change