skills/steipete/agent-scripts/oracle/Gen Agent Trust Hub

oracle

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx -y @steipete/oracle, which downloads and executes the package from the NPM registry. This package belongs to the verified author of the skill.
  • [COMMAND_EXECUTION]: The skill executes the oracle CLI to perform file system operations, such as reading directories and expanding globs, and to initiate network-based tasks for AI model reviews.
  • [DATA_EXFILTRATION]: By design, the tool bundles local file content and sends it to external LLM providers (e.g., OpenAI or Google). The instructions explicitly caution the user to redact secrets and use exclusion patterns to avoid sharing sensitive data like .env files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 06:37 AM