fluent-development

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a set of tools for ServiceNow development that interface with the official ServiceNow SDK (@servicenow/sdk). These tools operate locally on the developer's machine to manage project initialization, builds, and installations.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow for ingesting metadata from ServiceNow instances, which represents a potential attack surface for indirect prompt injection. 1. Ingestion points: Metadata downloaded via snow_fluent_download and processed via snow_fluent_transform as described in SKILL.md. 2. Boundary markers: None explicitly mentioned in the skill instructions. 3. Capability inventory: Local command execution for build and install tasks via snow_fluent_build and snow_fluent_install. 4. Sanitization: No specific sanitization or filtering of instance-provided metadata is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:16 PM
Security Audit — agent-trust-hub — fluent-development