trae-orchestrator
What this skill does
Orchestrates TRAE IDE for automated software development with multi-agent collaboration
github/leoyeai - System Prompt Leakage - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=trae-orchestratorAssessments (2)
System Prompt Leakage
System Prompt Leakage via local-llm-review
automation_helper.py
The code contains a function called '_find_trae' that attempts to locate the TRAE IDE executable by checking multiple hardcoded paths on Windows systems. This could be used to infer system structure oExcessive Agency
Excessive Agency via local-llm-review
automation_helper.py
The '_find_trae' function uses hardcoded paths that may not be appropriate for all user environments, potentially leading to unexpected behavior or failure if the TRAE IDE is installed in a non-standaBadge
Add the Anomity scan badge for trae-orchestrator 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 trae-orchestrator? Report an issue or request a rescan.
