The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to execute the just publish command on the host system to build, tag, and release software. This is the primary function of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the project's local environment which could influence the agent's behavior.
Ingestion points: The agent reads project-level configuration files including justfile, build.zig.zon, mix.exs, package.json, and Cargo.toml to extract version information and verify command availability.
Boundary markers: No explicit delimiters or instructions are used to separate the content of these files from the agent's instructions, nor are there warnings to ignore instructions embedded within those files.
Capability inventory: The skill allows for shell command execution (just publish) and provides detailed failure output to the user, which could be leveraged if a project file is maliciously crafted.
Sanitization: The skill does not sanitize or validate the content of the justfile or its recipes before attempting execution, relying instead on a user confirmation prompt.

publish