testing-evidence-collector

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (ls, grep, cat) and a local script (./qa-playwright-capture.sh) for inspecting project files and capturing screenshots of a locally running web server at http://localhost:8000. These operations are consistent with the skill's stated purpose of providing automated QA testing.
  • [SAFE]: No remote code downloads, data exfiltration to external domains, or hardcoded credentials were found. The prompt instructions focus on maintaining a skeptical persona to ensure thorough testing rather than attempting to bypass safety filters or ignore system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:44 AM
Security Audit — agent-trust-hub — testing-evidence-collector