setup-opencli
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs global installation of the
@jackwener/openclipackage via the NPM registry and usesnpx skills addto download and integrate five additional skill modules from thejackwener/openclirepository. - [COMMAND_EXECUTION]: The setup process requires the execution of shell commands to install software, verify the environment using
opencli doctor, and perform smoke tests that launch and interact with the Chrome browser. - [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by enabling the agent to interact with and extract data from live web pages.
- Ingestion points: Data enters the agent's context through the
opencli-browserskill which supports page navigation and data extraction (extract). - Boundary markers: The instructions do not define specific delimiters or safety warnings for the agent when processing external web content.
- Capability inventory: The skill suite grants the agent significant capabilities, including clicking, typing, form filling, and network observation within the user's authenticated browser session.
- Sanitization: No evidence of input sanitization or content filtering is provided in the configuration instructions.
Audit Metadata