research-swarm
What this skill does
The skill 'research-swarm' is a multi-agent coordinator for cancer research, assigning tasks to agents that search open-access databases and submit cited findings. It interacts with public research AP
github/leoyeai - Network Security - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=research-swarmAssessments (2)
Network Security
Network Security via local-llm-review
SKILL.md
The skill submits findings to 'https://www.researchswarm.org/api/v1/agents/{agentId}/findings' with no authentication, only an agent ID. This could be exploited if agent IDs are predictable or leaked,Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill sends 'title, summary, citations array, confidence rating, contradictions, gaps' to the public endpoint. If this data contains sensitive or proprietary information, it could be exfiltrated wBadge
Add the Anomity scan badge for research-swarm 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 research-swarm? Report an issue or request a rescan.
