opencli-explorer

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill describes a pattern for fetching configuration files from raw.githubusercontent.com to dynamically discover API parameters like GraphQL query IDs. This is a standard practice for maintaining scrapers and targets a well-known service.\n- [COMMAND_EXECUTION]: The instructions involve executing framework-specific CLI commands (opencli browser, opencli generate) and standard development scripts (npm run build). These are functional requirements for the development tasks described.\n- [REMOTE_CODE_EXECUTION]: The provided templates use browser automation APIs, specifically page.evaluate, to execute JavaScript within a target website's context. This is the intended behavior for site exploration and API verification.\n- [DATA_EXFILTRATION]: No evidence of unauthorized data transfer was found. Network operations are limited to legitimate API interactions and configuration fetching.\n- [PROMPT_INJECTION]: The skill contains instructional content for an AI agent but does not include patterns aimed at bypassing safety guardrails or overriding system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 05:30 PM