qa-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes Playwright automation commands such as
npx playwright testandplaywright-clito drive browser interactions. This is the intended primary function for verifying deployed services. - [DYNAMIC_EXECUTION]: Synthesizes TypeScript specifications (
.spec.ts) at runtime based on analyzed documentation and interactive probing, then executes these scripts using the Playwright test runner. - [INDIRECT_PROMPT_INJECTION]: The skill represents an indirect injection surface by ingesting contents from documentation files (
explore.md,work.md,verify.md) and browser DOM snapshots to derive testing logic. * Ingestion points: Documentation files and DOM snapshots. * Boundary markers: Absent. * Capability inventory: Shell execution and file system writes to.backend/. * Sanitization: Implements robust PII redaction for output artifacts but lacks explicit sanitization for ingested data. - [DATA_EXFILTRATION]: Handles sensitive artifacts including browser cookies, localStorage (
storageState.json), and network captures (HAR files). The skill includes mandatory redaction procedures for PII and Authorization headers to prevent credential leakage.
Audit Metadata