project-scaffolder

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input to determine the technology stack and project requirements, which could be exploited to influence agent behavior through malicious project descriptions.
  • Ingestion points: User input for tech stack specification or project context (SKILL.md, Core Workflow).
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within user requests.
  • Capability inventory: The agent has the ability to create folders and write files (scripts, configurations, and source code) to the file system.
  • Sanitization: Absent; the skill does not specify validation or sanitization steps for the user-provided requirements before code generation.
  • [DYNAMIC_EXECUTION]: The skill generates executable scripts, source code files (.ts, .tsx, .py, .ts), and configuration files (package.json, pyproject.toml) based on templates in references/templates.md. While these are generated from predefined patterns, the creation of executable content from user-driven specifications is a dynamic execution pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM
Security Audit — agent-trust-hub — project-scaffolder