The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to install the nib CLI by downloading a script from https://nibrun.com/install.sh and piping it directly to sh. This is a high-risk pattern that allows for arbitrary code execution and is vulnerable to supply-chain attacks if the remote server or the transport mechanism is compromised.
[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute various shell commands, including nib run, nib login, and binary build commands like bun build --compile. While these are core to the skill's functionality, they involve executing binaries that may be produced from untrusted repository content.
[INDIRECT_PROMPT_INJECTION]: The skill processes repository content (data provided at runtime) to build and deploy binaries, creating an attack surface where malicious instructions in the repository could influence the agent's behavior during the build or deployment phase.
Ingestion points: Project repository files, including source code, configuration files (e.g., .env.example), and build manifests.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the processed repository files.
Capability inventory: The skill utilizes shell command execution, file system access (reading code, writing binaries), and network operations via the nib CLI and curl.
Sanitization: There is no evidence of sanitization or validation of the repository content before it is used in build commands or environment variable configuration.

deploy-to-nibrun