The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes the @stevysmith/rive-generator package from the NPM registry. This package is a vendor-owned resource corresponding to the skill's author ('stevysmith').
[INDIRECT_PROMPT_INJECTION]: The skill is designed to translate natural language user requests (e.g., 'create Rive animation') into executable code. This creates an attack surface where an attacker could potentially embed malicious instructions within a design request.
Ingestion points: User prompts describing animation requirements (referenced in SKILL.md description).
Boundary markers: Absent from the provided instruction templates.
Capability inventory: The skill uses fs.writeFileSync to create files and instructs the agent to execute shell commands (node, npx tsc) to run generated scripts.
Sanitization: No explicit sanitization or validation logic for the generated code is provided in the skill instructions.
[DYNAMIC_EXECUTION]: The core workflow involves generating TypeScript or JavaScript source files and subsequently executing them using the Node.js runtime. While this is the intended functionality of a code generator, it involves the execution of dynamically created content.

rive-generator