playwright-validation

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill contains hardcoded default credentials ('admin@open-metadata.org' / 'admin') for use in local development and testing environments.
  • [COMMAND_EXECUTION]: The skill uses terminal commands such as 'git diff' to identify codebase changes and 'yarn lint:playwright' to perform quality checks on test files.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it instructs the agent to read and process external data from feature branches which could contain malicious instructions.
  • Ingestion points: Instructions in Phase 1 and Phase 2 require the agent to read file contents and diffs from repository branches.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the analyzed code files.
  • Capability inventory: The skill has access to terminal execution (git, yarn) and browser control through Playwright MCP tools.
  • Sanitization: No validation or sanitization is performed on the content ingested from the branch files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 06:14 PM