skills/niekcandaele/skills/tester/Gen Agent Trust Hub

tester

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a legitimate testing utility that provides clear reporting and strictly prohibits the agent from implementing fixes or code changes.
  • [PROMPT_INJECTION]: Analysis of the indirect prompt injection surface inherent to testing tools:
  • Ingestion points: The skill ingests and analyzes test logs from shell execution and web content via browser automation.
  • Boundary markers: The instructions do not define explicit boundary markers or delimiters to isolate untrusted tool output from the system prompt.
  • Capability inventory: The skill is granted access to high-privilege tools including shell access (Bash) and arbitrary JavaScript execution in the browser (Playwright evaluate).
  • Sanitization: There are no specified mechanisms for sanitizing or validating the content of test outputs or browser data before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 07:18 AM
Security Audit — agent-trust-hub — tester