The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git, node, pnpm, and shell scripts utilizing the Bash tool to manage branches and build dashboard assets. These operations are scoped to the project directory and the plugin's own installation path.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection as it ingests untrusted data from the project.
Ingestion points: Reads files from docs/unwind/** and uses the current working directory to generate the dashboard content.
Boundary markers: No specific delimiters or instructions to ignore embedded prompts are defined for the project documentation.
Capability inventory: The skill has permissions for command execution, file system manipulation, and remote code delivery (via Git push).
Sanitization: No sanitization or validation of the documentation content is mentioned in the skill instructions.

uw-publish