qwen-agent
What this skill does
Delegate menial, well-scoped coding tasks to a Qwen-backed subagent via the `claude-9arm` command
github/thananon - Security Misconfiguration - 3.1k stars
Threat analysis
Skill info
pkg:github/thananon/9arm-skills@a1fc303?skill=qwen-agentAssessments (2)
Security Misconfiguration
Security Misconfiguration via local-llm-review
SKILL.md
The `claude-9arm` alias is defined as `claude --model qwen3.6-35b-a3b` routed through the 9arm gateway. This could be a misconfiguration or a potential attack vector if the '9arm' gateway is not propeInsecure Defaults
Insecure Defaults via local-llm-review
SKILL.md
The alias bakes in `--allowedTools '*'`, which is explicitly noted to be silently ignored by Claude Code with a warning. This could lead to unexpected behavior or security risks if the intended alloweBadge
Add the Anomity scan badge for qwen-agent 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 qwen-agent? Report an issue or request a rescan.
