ux-cro-audit

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external, untrusted content, which creates a potential surface for indirect prompt injection.
  • Ingestion points: As defined in SKILL.md, the agent processes data from landing pages, pricing screens, in-app interfaces, competitor reviews, and support chat corpuses.
  • Boundary markers: The instructions do not define delimiters or provide clear directives to the agent to ignore instructions that might be embedded in the audited content.
  • Capability inventory: The skill focus is on generating audit reports and negotiation scripts; it does not include instructions for sensitive file access or network exfiltration, although it operates within an agent context with tool access.
  • Sanitization: No procedures for filtering or sanitizing harvested data are specified prior to analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:14 PM
Security Audit — agent-trust-hub — ux-cro-audit