agentforce-generate

Warn

Audited by Snyk on Aug 14, 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). In SKILL.md, the required runtime workflow includes sending user-provided utterances into sf agent preview send ... -u "<message>" and reading resulting live session traces (--use-live-actions), which exposes the agent to outsider-authored free text at runtime.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 14, 2026, 04:53 PM
Issues
1
Security Audit — snyk — agentforce-generate