skills/datex/skills/tailoring-overlay/Gen Agent Trust Hub

tailoring-overlay

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill facilitates the creation and modification of Datex Studio component configurations. All operations use the dxs CLI tool, which is a vendor-provided resource for interacting with the platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that ingests configuration data via the dxs configuration get command (SKILL.md) and processes it to create tailored overlays. While this ingestion represents a surface for potentially untrusted data, the risk is mitigated by the following factors: 1. Ingestion points: Configuration JSON is fetched from the platform's backend via CLI. 2. Boundary markers: The workflow uses structured JSON parsing and precise jq extraction rather than raw text interpolation. 3. Capability inventory: The skill can update platform state using the dxs configuration upsert command (SKILL.md). 4. Sanitization: The process includes a mandatory dxs configuration validate step (SKILL.md) which enforces schema constraints and prevents the deployment of malformed or unauthorized configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 06:14 PM
Security Audit — agent-trust-hub — tailoring-overlay