cypress-author

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs a version check by executing npx cypress --version in the project root if the Cypress version cannot be determined from the package.json file.
  • [DATA_EXPOSURE]: The skill accesses local project metadata, including package.json, cypress.config.js, and existing spec files. This is used to maintain consistency with the project's coding style and language (TypeScript vs JavaScript).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local repository (existing test files and configuration) to inform its code generation. While this represents a potential surface for indirect prompt injection if a user were to open a malicious repository, the skill's capabilities are limited to local file authoring and do not involve network exfiltration or high-privilege system modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 02:08 PM
Security Audit — agent-trust-hub — cypress-author