agent-e2e-test-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it is designed to ingest and process untrusted project data such as code and diffs to generate test cases and browser commands.
- Ingestion points: The agent is instructed in the SKILL.md instructions to review project diffs and existing code to validate and write new tests.
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined in the instructions for the ingestion of untrusted project code.
- Capability inventory: The skill involves writing new test files (scaffolding, page objects) and executing browser automation commands via Playwright or Cypress CLI tools.
- Sanitization: No explicit sanitization or filtering of the ingested external project content is mentioned.- [EXTERNAL_DOWNLOADS]: The skill includes instructions and GitHub Action examples that download and install Playwright browser binaries and system dependencies using the standard "npx playwright install" command, which fetches assets from well-known official sources.
Audit Metadata