conduxt
What this skill does
Orchestrate full-duplex coding agent sessions via ACPX or tmux, composing OpenClaw native tools and community Skills. Handles any coding task: requirements, bug fixes, refactoring, investigations.
github/leoyeai - Tool Misuse - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=conduxtAssessments (4)
Tool Misuse
Tool Misuse via local-llm-review
scripts/launch.sh
The script uses 'nohup' which can be used to run processes in the background even after the user logs out. This could be used to persist processes or hide malicious activity.Excessive Agency
Excessive Agency via local-llm-review
scripts/launch.sh
The script allows for the execution of arbitrary agent commands without explicit user confirmation, which could lead to unintended behavior.Excessive Agency via local-llm-review
scripts/setup.sh
The script automatically creates git branches and worktrees based on task IDs and descriptions, which could lead to unintended changes in the repository.Excessive Agency via local-llm-review
scripts/watchdog.sh
The script automatically monitors and recovers tasks without explicit user confirmation, which could lead to unintended behavior.Badge
Add the Anomity scan badge for conduxt 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 conduxt? Report an issue or request a rescan.
