applying-cms-brand

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it is designed to ingest and strictly follow instructions retrieved from Salesforce CMS.
  • Ingestion points: Data is retrieved via search_brands and get_brand_instructions tools as described in SKILL.md.
  • Boundary markers: Instructions do not specify delimiters to isolate retrieved brand data from the agent's core instructions.
  • Capability inventory: The skill influences content generation and applies retrieved rules to the agent's output.
  • Sanitization: No explicit validation or filtering of the retrieved CMS content is performed before use.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 02:37 AM
Security Audit — agent-trust-hub — applying-cms-brand