web-utilities-vueuse
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the
@vueuse/corepackage throughout its documentation and examples. This is a well-known and widely used open-source library for Vue developers. The imports are handled standardly and do not involve untrusted remote scripts or unverified third-party registries. - [INDIRECT_PROMPT_INJECTION]: The skill demonstrates patterns for fetching data from external APIs and sockets (e.g.,
useFetch,useWebSocket,useEventSource). While these represent potential ingestion points for untrusted data into an agent's context, the skill itself does not provide any dangerous capabilities that could be triggered by such data. - Ingestion points:
examples/network.md(viauseFetch,useWebSocket, anduseEventSourcepatterns). - Boundary markers: None defined in the pattern examples.
- Capability inventory: The skill is restricted to UI and browser-state utilities; it does not implement subprocess execution, file system writes, or other sensitive operations.
- Sanitization: The examples use standard parsing (e.g.,
JSON.parse) without extra sanitization layers, which is standard for a utility reference library.
Audit Metadata