pinia-store-setup
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on user-provided requests and project files related to Pinia store setup without utilizing explicit boundary markers or sanitization, which presents an attack surface for indirect prompt injection.
- Ingestion points: The skill processes user queries and project-related files (Vue/Pinia store definitions) during the development workflow.
- Boundary markers: There are no instructions defining delimiters or warnings to ignore instructions embedded within the data files it reads.
- Capability inventory: The skill has broad capabilities including file modification (
Write,Edit) and arbitrary shell command execution (Bashwith unrestricted parameters), which could be misused if the agent obeys instructions found in external data. - Sanitization: No validation or filtering mechanisms are specified for content ingested from the development environment.
- [NO_CODE]: The skill contains only instructional text and configuration metadata within the SKILL.md file; it does not include or execute any attached scripts, binaries, or source code files.
Audit Metadata