The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads UI components and layout blocks from the shadcn registry and vendor-specific libraries using npx and pnpm. These operations target well-known and trusted package registries within the developer ecosystem.
[COMMAND_EXECUTION]: The agent is directed to perform various shell operations, including package installation, project builds, and starting development servers through pnpm, as well as executing a custom testing tool (/iblai-test).
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: The agent is directed to analyze content from codebase files such as README.md and CLAUDE.md, and process responses provided by the user during the discovery phase. Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between its primary instructions and potentially adversarial content within the ingested files. Capability inventory: The skill possesses the ability to write new files to the filesystem and execute shell commands through npx and pnpm. Sanitization: There is no evidence of content validation, escaping, or filtering applied to the external data before it is interpolated into the agent's context.

iblai-landing