The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx shadcn@latest add to install logo components into the local project.
Evidence: The Install Pattern and Quick Patterns sections in SKILL.md use npx shadcn@latest add @elements/{name}-logo.
[EXTERNAL_DOWNLOADS]: The skill downloads code components from the @elements scoped registry via the shadcn CLI. These resources are hosted on the author's infrastructure (tryelements.dev and GitHub).
Evidence: References to @elements/ packages and the https://tryelements.dev/docs/logos URL.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied brand names by interpolating them into shell commands, creating a vulnerability surface where a malicious user could attempt command injection through the {name} placeholder.
Ingestion points: User-provided company names from queries like "logo for [company]" or "add [company] logo" (identified in SKILL.md triggers).
Boundary markers: Absent. The skill does not provide instructions to the agent to validate or sanitize the {name} variable before execution.
Capability inventory: The skill uses npx for package installation and ls / sed for registry scanning, which involve shell command execution.
Sanitization: Absent. There are no instructions to escape or filter user input before it is placed in the npx command string.

tech-logos