Playwright Network HAR Recorder

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is installed from the vendor's official repository ('agentskillexchange') using established ecosystem commands.
  • [SAFE]: The 'security_reviewed' claim in the metadata is a self-assertion by the author and is documented as unverified per security analysis protocols.
  • [PROMPT_INJECTION]: The skill processes network traffic data (HAR files) which represents an external data source, creating an indirect prompt injection surface.
  • Ingestion points: Captures and replays network traffic from arbitrary external URLs.
  • Boundary markers: No explicit delimiters or instruction-bypass warnings are mentioned in the configuration.
  • Capability inventory: High-privilege browser automation and network interception via Playwright's routeFromHAR API.
  • Sanitization: Provides mechanisms to redact sensitive patterns such as authentication tokens and PII from the recorded data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:35 AM