playwright-test-generator
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
npx tscfor type checking andnpx playwright testfor test verification during the final stage of the pipeline.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted external content. - Ingestion points: The skill reads local project files (routing, source code, and configurations) in Step 2 and performs browser exploration of live web pages in Step 3.
- Boundary markers: There are no explicit instructions or delimiters (such as XML tags or clear 'ignore instructions' warnings) used when the agent processes content from source files or DOM snapshots.
- Capability inventory: The skill possesses the ability to write new files to the filesystem, execute arbitrary shell commands via the test runner, and invoke other agent skills like
e2e-reviewer. - Sanitization: While Step 3 advises against pasting raw content into responses, there is no formal sanitization or validation of the ingested text before it influences the scenario design and code generation phases.
Audit Metadata