backward-compatibility-reviewer

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.95). The skill's required workflow (Step 4 in SKILL.md and the Telemetry Analysis Reference) instructs the agent to query the Keboola telemetry tables (e.g., KBC_USE4_37.out.c-kbc_public_telemetry) and read user-provided configuration_json from many external projects, which is untrusted user-generated content that the agent must parse and use to decide risk/severity — enabling indirect prompt-injection via telemetry data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 10:33 AM