Skills
Navigate
skills/yuniorglez/gemini-elite-core/e2e-testing-expert/Gen Agent Trust Hub

e2e-testing-expert

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external URLs, creating a surface for indirect prompt injection.
  • Ingestion points: The scripts/generate-pom.ts script and general instructions suggest processing a URL's accessibility tree to scaffold code.
  • Boundary markers: The instructions lack explicit boundary markers or warnings to the agent regarding the untrusted nature of external web content.
  • Capability inventory: The skill facilitates file system writes (POM generation) and shell command execution (playwright test).
  • Sanitization: There are no documented procedures for sanitizing or escaping content fetched from external sources before it is used in code generation.
  • [COMMAND_EXECUTION]: The skill uses shell commands for its core functionality.
  • Evidence: Instructions include running bun x playwright test and utilizing local scripts such as scripts/analyze-traces.sh to manage test results and debugging tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 08:18 AM