The Agent Skills Directory

[PROMPT_INJECTION]: Indirect Prompt Injection Surface
Ingestion points: The skill is specifically designed to analyze, review, and refactor user-provided Svelte code as described in the instructions and examples (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions potentially embedded within the code samples it reviews.
Capability inventory: The skill is configured with access to powerful tools including Bash, Write, and Edit, which could be exploited if an indirect injection successfully overrides agent behavior (SKILL.md).
Sanitization: The instructions do not define any sanitization or validation steps for external code content before it is processed by the agent.

svelte-expert