mentor
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: 0.80). The skill explicitly accepts a CV or LinkedIn "archivo o link" as input, so the agent may ingest/read public LinkedIn profiles or user-provided CVs (untrusted, user-generated third‑party content) as part of its workflow, which could enable indirect prompt injection.
Audit Metadata