harness-code-integration

Warn

Audited by Snyk on Feb 27, 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). The skill explicitly clones and reads Harness Code repositories and webhook payload fields (e.g., "cloneCodebase: true" in the PR Validation Pipeline, manifests with store type: HarnessCode, and the use of <+trigger.payload.*> expressions), so untrusted repository contents and webhook payloads provided by external users could be ingested and directly influence pipeline actions and deployments.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 07:27 PM