amazon-alexa-qa
What this skill does
Automation of question submission to Amazon's Alexa/Rufus AI shopping assistant and collection of structured response data.
github/browser-act - Data Exfiltration - 5.3k stars
Threat analysis
Skill info
pkg:github/browser-act/skills@4577dc5?skill=amazon-alexa-qaAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/extract-response.py
The script extracts and returns the question and response text from the Alexa/Rufus interface, which could be used to exfiltrate user data if the skill is misused or compromised.UI Manipulation
UI Manipulation via local-llm-review
scripts/inject-question.py
The script injects a question into the Alexa/Rufus interface by directly manipulating the DOM and simulating user input, which could be used to inject malicious content or bypass user controls.Badge
Add the Anomity scan badge for amazon-alexa-qa 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 amazon-alexa-qa? Report an issue or request a rescan.
