convex-create-component

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user or agent to run official Convex CLI tools, including npx convex dev and npx convex codegen, which are essential for the platform's development workflow and code generation.
  • [EXTERNAL_DOWNLOADS]: The skill references standard ecosystem packages such as @convex-dev/auth and convex-helpers. These are well-known libraries within the Convex developer community and are used here according to their intended functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface where it processes user-provided descriptions of desired features to generate code and component structures.
  • Ingestion points: User input regarding the feature goals and project context in SKILL.md.
  • Boundary markers: None explicitly defined in the prompt templates.
  • Capability inventory: The skill performs file system writes to create components and executes shell commands via the Convex CLI (SKILL.md).
  • Sanitization: No explicit sanitization of user input is described before generating code. This represents a low-severity risk typical of coding assistant tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:38 PM
Security Audit — agent-trust-hub — convex-create-component