salary-research
Warn
Audited by Snyk on May 1, 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). Yes — SKILL.md Step 1 explicitly directs the agent to use WebSearch to fetch and extract salary reports from public, user-generated sites (Levels.fyi, Glassdoor, Blind, Payscale), and those extracted reports are then synthesized into compensation guidance that can materially influence negotiation actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata