agent-team-builder
What this skill does
The skill is a configuration and setup tool for building multi-agent teams on the OpenClaw platform. It guides users through creating agents, defining roles, setting up workspaces, and configuring rou
github/leoyeai - Insecure Configuration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=agent-team-builderAssessments (2)
Insecure Configuration
Insecure Configuration via local-llm-review
references/openclaw-team-example.json5
The configuration file contains a placeholder for a long random token (`"token": "REPLACE_WITH_LONG_RANDOM_TOKEN"`). If this token is not properly replaced with a secure, unique value, it could lead tDocumentation Risk
Documentation Risk via local-llm-review
references/team-shared-memory.md
The document references a GitHub issue (#24832) that proposes a `sharedContextFiles` mechanism. While this is not yet implemented, the mention of a potential future feature that could allow shared filBadge
Add the Anomity scan badge for agent-team-builder 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 agent-team-builder? Report an issue or request a rescan.
