The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a dynamic context injection shell command (!cat package.json | grep ...) to read the project's package.json file to pre-load version information for dependencies into the context.
[PROMPT_INJECTION]: The skill instructs the agent to fetch and process content from external documentation sites, creating a surface for indirect prompt injection. * Ingestion points: External documentation URLs fetched using WebFetch. * Boundary markers: Absent; no specific instructions to ignore embedded prompts are provided in the skill. * Capability inventory: The agent can read local files and fetch web content. * Sanitization: Absent; the skill does not specify filtering or validation of documentation content.

source-driven