create-verification-skill
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes the target repository to generate a verification skill by reading files such as package.json, e2e.config.ts, and existing test suites. This ingestion of untrusted repository data creates a surface for indirect prompt injection. Ingestion points include package.json, e2e.config.ts, Playwright/Cypress suites, and documentation. No explicit boundary markers or sanitization steps are defined for processing this content. Capabilities include writing files to the .agents/skills/ directory and executing shell commands via the e2e CLI.- [COMMAND_EXECUTION]: The skill instructs the agent to execute several commands during the verification phase, including npx e2e list, npx e2e run, and npx e2e explore. These commands execute the application and generated tests within the local environment.- [DYNAMIC_EXECUTION]: The skill generates new test files, such as tests/smoke.e2e.ts, and immediately executes them to prove the functionality of the generated verification skill.- [EXTERNAL_DOWNLOADS]: The skill references the installation of external tools using npx skills add e2e-inc/e2e and npx e2e init. These resources are maintained by the skill author (e2e-inc).
Audit Metadata