kelly-ecommerce-intel

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests data from external e-commerce platforms and news sources to generate intelligence signals.\n
  • Ingestion points: Browsing of public marketplace and competitor URLs as defined in SKILL.md.\n
  • Boundary markers: Implements a mandatory human-review gate in the Busabase App UI where all signals, actions, and drafts require operator approval.\n
  • Capability inventory: Capable of drafting listing copy, ad angles, and customer responses; writes records to Busabase bases.\n
  • Sanitization: Employs HTML escaping and structured data validation for all content displayed in the UI to prevent execution of embedded data.\n- [EXTERNAL_DOWNLOADS]: Utilizes standard SDKs and server frameworks for its core functionality.\n
  • Node packages: busabase-sdk@0.11.0, hono, @hono/node-server, esbuild-wasm.\n
  • Dependencies: Fetches required libraries from standard package registries and utilizes official vendor infrastructure for data synchronization.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 10:36 AM
Security Audit — agent-trust-hub — kelly-ecommerce-intel