firehydrant

Warn

Audited by Snyk on Apr 29, 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’s required workflow instructs the agent to connect via the Membrane CLI to FireHydrant and to run/list actions that return FireHydrant data (incidents, runbooks, artifacts) from a third‑party service (see "Connecting to FireHydrant" and "Running actions" in SKILL.md), which are user-generated/untrusted content the agent is expected to read and that could materially influence subsequent decisions or actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 04:19 AM
Issues
1