roundtable-adaptive
What this skill does
Adaptive multi-model AI roundtable for debate and consensus scoring, using multiple AI models including Claude, GPT, Grok, and Gemini.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=roundtable-adaptiveAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill requires and stores API keys in environment variables (ANTHROPIC_API_KEY, OPENAI_API_KEY) and potentially sends them to external services (e.g., Blockrun proxy). This is a potential risk if Configuration Risks
Configuration Risks via local-llm-review
SKILL.md
The skill allows configuration of external proxies (e.g., BLOCKRUN_PROXY_URL) which could be used to route traffic through untrusted or malicious endpoints.Badge
Add the Anomity scan badge for roundtable-adaptive 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 roundtable-adaptive? Report an issue or request a rescan.
