dev-vueuse

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements standard development patterns for the VueUse library, a well-known and trusted utility collection for Vue.js.
  • [DATA_EXPOSURE]: Provides patterns for using browser storage (useLocalStorage, useSessionStorage) and clipboard access (useClipboard). These are standard web development practices for application state persistence and user interaction. No credentials or sensitive system files are accessed.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines ingestion points for external data via clipboard pasting and local storage imports.
  • Ingestion points: Found in src/composables/useTaskClipboard.ts (clipboard paste) and src/composables/usePersistentTasks.ts (local storage/JSON import).
  • Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore instructions embedded within imported data.
  • Capability inventory: The skill is limited to managing reactive UI state and internal application logic. There are no patterns for subprocess execution, arbitrary file system writes, or network exfiltration of sensitive data.
  • Sanitization: Includes basic JSON parsing and string manipulation; however, given the benign capability set, the risk surface is minimal.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 01:14 AM
Security Audit — agent-trust-hub — dev-vueuse