Nova Resource Builder
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (MEDIUM): The skill triggers shell commands (php artisan) and local script execution (./scripts/dev.sh) using the Bash tool with parameters derived from agent context. Evidence: SKILL.md lines 24, 27, and 29. Risk: Without explicit sanitization of variables like ResourceName, the skill is vulnerable to command injection if the input is influenced by malicious third-party content.
- [COMMAND_EXECUTION] (MEDIUM): The skill establishes an indirect prompt injection surface due to the combination of filesystem access and high-privilege execution tools. Ingestion points: The agent uses Read, Grep, and Glob tools to analyze local project files (SKILL.md frontmatter). Boundary markers: The skill does not define delimiters or provide instructions to ignore embedded commands within processed files. Capability inventory: The skill utilizes Bash, Write, and Edit tools to modify the system state. Sanitization: No sanitization or validation logic is defined for the data ingested from files before it is processed by other tools.
Audit Metadata