analyze-oss
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly clones arbitrary public GitHub repositories (Phase 1:
git cloneinto ~/opensource-analysis/), then instructs the agent and parallel subagents to read README, package files, examples, commits, and other repo content (Phase 2/3), so untrusted, user-generated third‑party content is ingested and used to drive analysis and agent outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata