brand-research-agent

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Prompt Injection] (LOW): All agents in this skill are susceptible to Indirect Prompt Injection (Category 8) because they are designed to ingest and analyze untrusted external data. * Ingestion points: External brand websites, testimonials, and product catalogs. * Boundary markers: Absent; the prompts lack explicit delimiters to separate analyzed data from agent instructions. * Capability inventory: None; the skill contains no scripts, tool definitions, or file-write/network capabilities. * Sanitization: Absent; there is no instruction to validate or escape processed content.
  • [No Code] (SAFE): The skill is composed entirely of Markdown instruction files. There are no executable scripts, binaries, or configuration files present, which eliminates traditional code execution attack vectors.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:31 PM