sveltekit-data-flow
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 1.00). The prompt includes an HTML-comment "LLM WORKFLOW" with hidden editing/CLI instructions for an agent (e.g., "Write/edit SKILL.md", "Run: claude-skills-cli validate") that are unrelated to the skill's stated SvelteKit guidance and therefore constitute deceptive/hidden instructions outside the skill's purpose.
Audit Metadata