blazor-interactive-ssr-adhoc-testing-playwright-cli

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or workflows.
  • [COMMAND_EXECUTION]: The skill provides examples of shell commands to be executed via playwright-cli, targeting local development environments by default (e.g., localhost:5001).
  • [INDIRECT_PROMPT_INJECTION]: The skill uses tools that ingest data from potentially untrusted web pages, creating an attack surface for indirect prompt injection. (1) Ingestion points: playwright-cli eval, playwright-cli snapshot, playwright-cli console, and playwright-cli network in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: playwright-cli click, playwright-cli fill, and playwright-cli run-code in SKILL.md. (4) Sanitization: Absent.
  • [DYNAMIC_EXECUTION]: The skill uses playwright-cli eval and playwright-cli run-code to execute JavaScript within the browser context for UI testing purposes, which is standard functionality for this type of tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:17 PM