user-research
Fail
Audited by Snyk on Mar 3, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 1.00). The workflow's step 7 directs saving reports to internal .claude/context/... paths (internal assistant storage), which is an instruction to persist data into the agent's environment that is outside the declared UX-research outputs and looks like a hidden/deceptive directive to write/exfiltrate internal context.
Audit Metadata