integration-management

Warn

Audited by Snyk on Jul 3, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via Mode 2 “Connected repository” where the skill “read[s] each contract” from a user-provided external folder/VDR and extracts assignment/change-of-control clause text, which is attacker-controlled prose from non-user-authored documents.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 3, 2026, 03:58 PM
Issues
1
Security Audit — snyk — integration-management