meridian
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download the project source code from the author's GitHub repository (github.com/zephyrwang6/VaultPilot.git).
- [COMMAND_EXECUTION]: The skill utilizes shell commands to manage the project environment, including cloning repositories, installing packages via
npm install, and running a local development server. It also uses thecatcommand to read design templates from the local filesystem. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external data (local design files) which is then interpolated into code generation tasks.
- Ingestion points: Reading local reference files via
catin SKILL.md. - Boundary markers: Not used.
- Capability inventory: File system writes to create components and modify project routing, plus full shell command execution for build and run tasks.
- Sanitization: Not used.
Audit Metadata