pal
Fail
Audited by Snyk on Aug 26, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill contains coercive workflow directives that mandate using a specific external model (anthropic/claude-opus-4.6) and force multi-step completion rules, which is suspicious steering without clear malicious intent.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata