agent-avengers
What this skill does
Multi-agent orchestration for task decomposition, execution, and consolidation. It automates complex tasks by dynamically creating and managing specialized agents.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=agent-avengersAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/execute.py
The function 'generate_openclaw_commands' is incomplete and not shown in the provided source. If this function generates commands that send data to external hosts or execute untrusted code, it could bInsecure File Handling
Insecure File Handling via local-llm-review
scripts/assemble.py
The script creates mission directories and files without checking for potential path traversal or injection vulnerabilities.Insecure File Handling via local-llm-review
scripts/consolidate.py
The script reads and writes mission.json and execution_plan.json without validating or sanitizing input, which could lead to data corruption or injection attacks.Badge
Add the Anomity scan badge for agent-avengers 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-avengers? Report an issue or request a rescan.
