svelte-ui-animator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill instructs the agent to analyze project files such as package.json and tailwind.config.js to identify existing setups and plan animations. While processing untrusted project files is a surface for indirect prompt injection, it is necessary for the skill's primary function and is mitigated by standard LLM guardrails.
  • Ingestion points: src/routes/, package.json, and tailwind.config.js in Phase 1 (Analyze).
  • Boundary markers: None explicitly mentioned in the instructions to the agent.
  • Capability inventory: File reading (analysis) and code generation/file writing (Phase 3: Implementation).
  • Sanitization: Not explicitly mentioned in the prompt logic.
  • Metadata Consistency (SAFE): The references/component-checklist.md file contains example directory structures using Next.js patterns (e.g., app/page.tsx), while the overall skill and SKILL.md are focused on Svelte/SvelteKit. This appears to be a documentation template inconsistency rather than a deceptive practice or metadata poisoning.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 09:22 PM