monitor-ci

Warn

Audited by Snyk on Mar 10, 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). The skill explicitly spawns subagents that call the ci_information MCP to fetch heavy fields like "taskOutputSummary", "suggestedFix", and "suggestedFixDescription" (FETCH_HEAVY subagent) from Nx Cloud and then analyzes those contents to decide and execute actions (apply/reject fixes, run local patches), so untrusted third-party CI/self‑healing content can directly influence tool use and next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 05:22 PM