fancy-ui-craft
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/_skill_cli.pyimplements arun_commandhelper usingsubprocess.runto execute shell commands. This utility is intended for project-level operations such as package management or build tasks as described in the skill documentation. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify existing project source code (Vue components and CSS), which introduces a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Local project files (e.g.,
.vue,.cssfiles) are read and processed by the agent. - Boundary markers: No explicit XML delimiters or specific 'ignore instructions' warnings are defined for the ingested file content.
- Capability inventory: The skill has the capability to execute shell commands via the
subprocess.runimplementation inscripts/_skill_cli.pyand install external packages. - Sanitization: There is no evidence of automated sanitization or filtering of instructions embedded within the source code being analyzed.
Audit Metadata