opencli-adapter-author
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external websites, which is a potential entry point for indirect prompt injection. The skill mitigates this by providing rigorous procedures for contract validation, data de-identification, and security-focused 'Deep Recon' protocols.
- [DYNAMIC_EXECUTION]: The skill facilitates the creation and execution of JavaScript adapter files in the user's local directory (
~/.opencli/clis/). This is the core functionality of the skill and is documented with verification steps to ensure reliability. - [COMMAND_EXECUTION]: The skill leverages specific platform tools (
opencli,jsluice) to perform technical analysis of target websites. These operations are restricted to the tool's intended scope.
Audit Metadata