macrocli
What this skill does
GUI automation and macro execution tool for interacting with applications via screenshots, keyboard shortcuts, and accessibility APIs.
github/hkuds - Data Exfiltration - 46.9k stars
Threat analysis
Skill info
pkg:github/HKUDS/CLI-Anything@39634a6?skill=macrocliAssessments (5)
Data Exfiltration
Data Exfiltration via local-llm-review
agent-harness/cli_anything/macrocli/backends/native_api.py
os.environ.copy() - copying environment variables may expose sensitive data (e.g., API keys, credentials) to the macro execution context.Data Exfiltration via local-llm-review
agent-harness/cli_anything/macrocli/backends/semantic_ui.py
os.environ.copy() - copying environment variables may expose sensitive data (e.g., API keys, credentials) to the macro execution context.Data Exfiltration via local-llm-review
agent-harness/cli_anything/macrocli/backends/visual_anchor.py
os.environ.copy() - copying environment variables may expose sensitive data (e.g., API keys, credentials) to the macro execution context.Data Exfiltration via local-llm-review
agent-harness/cli_anything/macrocli/core/recorder.py
os.environ.copy() - copying environment variables may expose sensitive data (e.g., API keys, credentials) to the macro execution context.Privilege Escalation
Privilege Escalation via local-llm-review
agent-harness/DEMO.md
sudo - use of 'sudo' in documentation may indicate potential for privilege escalation if not carefully controlled.Badge
Add the Anomity scan badge for macrocli 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 macrocli? Report an issue or request a rescan.
