safe-review

Warn

Audited by Snyk on Feb 15, 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's Template Review workflow requires the agent to read and perform a clause-by-clause comparison of a user-uploaded SAFE agreement (the uploaded third-party document), meaning it ingests untrusted/user-provided content as part of its processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:36 PM