website-usability-test-nova-act
What this skill does
AI-orchestrated usability testing using Amazon Nova Act. The agent generates personas, runs tests to collect raw data, interprets responses to determine goal achievement, and generates HTML reports. T
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=website-usability-test-nova-actAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/dynamic_exploration.py
The script collects raw responses from website testing, which may include sensitive data visible on tested pages. The skill writes test results to `test_results_adaptive.json` and generates HTML reporPrivacy Risk
Privacy Risk via local-llm-review
SKILL.md
The skill accesses and reads the user's Amazon Nova Act API key from `~/.openclaw/config/nova-act.json`, which is a sensitive credential. This is not inherently malicious, but it does involve handlingBadge
Add the Anomity scan badge for website-usability-test-nova-act to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of website-usability-test-nova-act? Report an issue or request a rescan.
