vertical-construction

Warn

Audited by Snyk on Jun 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow ingests outsider-authored free text via field-docs “Daily log” entries (crew/field notes are free-form text authored by people other than the operating user), which the agent would then include in the LLM context for processing/analysis.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 25, 2026, 04:10 AM
Issues
1
Security Audit — snyk — vertical-construction