expo-cicd-workflows

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches JSON schemas and syntax documentation from official Expo domains (api.expo.dev) and their public GitHub repository (github.com/expo/expo).
  • [COMMAND_EXECUTION]: Executes local Node.js utility scripts (fetch.js and validate.js) to process documentation and perform file validation, which involves installing standard dependencies from the npm registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-level workflow files, which is a standard surface for indirect prompt injection.
  • Ingestion points: The validate.js script reads YAML files located in .eas/workflows/.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands were identified in the script logic.
  • Capability inventory: The skill has capabilities for network fetching, local file reading, and writing to a local cache directory.
  • Sanitization: The tool uses js-yaml.load(), which is the safe version of the YAML parser and prevents code execution during deserialization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:20 PM
Security Audit — agent-trust-hub — expo-cicd-workflows