NYC

ecosystem-patterns

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill instructs the agent/tooling to fetch and consume user-provided/open-source repositories and GitHub PR data (e.g., "imi clone {repo-url}", use of "gh pr view" and the "github-mcp" mapping), so the agent will read and interpret untrusted, user-generated third‑party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:44 AM