The Agent Skills Directory

[SAFE]: The skill provides instructional content and Vue 3 code samples for using the TanStack DB library. The analysis found no evidence of malicious intent, unauthorized command execution, or data exfiltration. The use of the term 'CRITICAL' within the documentation refers to a common development mistake (missing reactive dependencies) and is not a prompt injection attempt.
[INDIRECT_PROMPT_INJECTION]: The skill defines patterns for fetching and displaying data from external database collections via the useLiveQuery composable.
Ingestion points: Data is ingested from database collections (e.g., todoCollection, projectsCollection, issuesCollection) through query functions defined in SKILL.md.
Boundary markers: None are present in the provided examples.
Capability inventory: The examples demonstrate data querying and reactive UI rendering; no dangerous capabilities like file system writes, network requests to untrusted domains, or shell execution are present in the scripts.
Sanitization: No explicit sanitization or input validation is shown in the examples. While this represents a theoretical attack surface common to all database-driven UI frameworks, it is the primary intended function of the library and does not constitute a security violation.

vue-db