gtm-icp

Warn

Audited by Snyk on Aug 26, 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). The runtime reads and scans repo-local freeform Markdown ICP artifacts (and stray placements) in the Doctor flow, so outsider-authored text can reach the LLM via user-submitted repository content that the workflow ingests (e.g., icps/*/ICP.md / legacy icps/*.md), even if not forced delivery beyond what is already in the repo.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 06:29 PM
Issues
1
Security Audit — snyk — gtm-icp