The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is instructed to execute npx storybook skills stories and adopt the resulting output as a "mandatory, ordered workflow". This creates a mechanism where external command output can influence the agent's operational logic. * Ingestion points: Command output from npx storybook skills stories and npx storybook tools docs. * Boundary markers: None; instructions specify reading the output in its "entirety". * Capability inventory: Execution of shell commands via npx, file system interaction, and network port binding. * Sanitization: No sanitization or validation of the CLI output is described.
[COMMAND_EXECUTION]: The skill relies on npx to run Storybook CLI tools. These commands are used to discover documentation, manage workflows, and start development servers. As these are provided by the skill's vendor, the usage is consistent with the skill's purpose.
[PRIVILEGE_ESCALATION]: The instructions advise the agent to "request escalated permissions" if the environment restricts network access or ports. This indicates a potential for the skill to operate with elevated privileges if granted by the user or host system.

stories