candidate-screening

Warn

Audited by Snyk on Apr 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: 1.00). The SKILL.md explicitly instructs pulling candidate data from Greenhouse ("pull candidates from Greenhouse manually or via the Greenhouse API" in Step 1) and to include external LinkedIn links in deep-dive reports (Step 3), so the agent is expected to ingest user-generated third-party content (applicant profiles/public LinkedIn pages) that can directly influence screening decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 02:57 PM
Issues
1
Security Audit — snyk — candidate-screening