skills/ansteorra/kmp/webapp-testing/Gen Agent Trust Hub

webapp-testing

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [External Downloads] (LOW): The skill documentation in SKILL.md states that 'Playwright will be installed automatically if not present'. Playwright is a trusted library maintained by Microsoft, so the finding is downgraded per trust rules.
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest data from external, potentially untrusted web pages through browser logs and page content analysis.
  • Ingestion points: The captureConsoleLogs function in test-helper.js collects all browser console messages, and SKILL.md examples show reading page titles and content.
  • Boundary markers: No explicit delimiters or instructions are used to prevent the agent from interpreting page content as new commands.
  • Capability inventory: The skill has the ability to write files to the local system (page.screenshot) and perform further network interactions via the browser.
  • Sanitization: There is no sanitization or filtering of text retrieved from the browser before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 04:16 AM