feature-builder

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied feature descriptions to plan and generate code. This is an indirect prompt injection surface inherent to the skill's purpose as an AI coding assistant.
  • Ingestion points: User-provided descriptions (e.g., 'Add login') in SKILL.md.
  • Boundary markers: None present to distinguish instructions from user data.
  • Capability inventory: Writing files, creating API endpoints, and database modifications.
  • Sanitization: No explicit sanitization of input is defined.
  • [COMMAND_EXECUTION]: The skill's implementation process involves generating API endpoints and database changes, which implies the execution of software development tools and shell commands for integration and testing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:05 AM
Security Audit — agent-trust-hub — feature-builder