update-brand-kit

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the creation of persistent instructions based on untrusted user input, which presents a surface for indirect prompt injection.
  • Ingestion points: Natural-language requests for brand updates and product descriptions defined in SKILL.md.
  • Boundary markers: None present; there are no instructions to use delimiters or ignore embedded commands within user-provided text.
  • Capability inventory: The skill is entirely instructional and does not contain scripts or code; it relies on the host platform for execution and persistence.
  • Sanitization: While the skill validates hex color formats and item limits, it lacks sanitization or filtering for the natural language content of the brand instructions.
  • [NO_CODE]: The skill does not provide any executable code or scripts, consisting only of instructions and metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 12:54 PM
Security Audit — agent-trust-hub — update-brand-kit