The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions direct the installation of the @jackwener/opencli NPM package and the cloning of the jackwener/OpenCLI repository from GitHub to establish the tool's environment.
[REMOTE_CODE_EXECUTION]: The skill provides commands for installing third-party plugins directly from any GitHub repository using opencli plugin install github:user/repo, which allows for the execution of unverified external code within the local environment.
[COMMAND_EXECUTION]: The skill utilizes the opencli external install command to download and configure various external CLI tools (such as gh, docker, and vercel), which typically involves running system-level installation scripts and package managers.
[PROMPT_INJECTION]: The skill possesses a broad attack surface for indirect prompt injection as it is designed to scrape and extract content from arbitrary websites and applications via opencli browser and specialized site adapters.
Ingestion points: Untrusted content from websites and applications is ingested through browser-driving subcommands such as extract, find, and network in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters provided to signal the agent to ignore potentially malicious instructions embedded in the extracted web content.
Capability inventory: The skill allows for significant system interaction through the Bash(opencli:*) tool, including browser automation, network request interception, and file system access to the ~/.opencli/ directory.
Sanitization: The instructions do not define any filtering or validation processes for the data retrieved from external sources before it is processed by the agent.

opencli-usage