orchestrator
Use when delegating coding or repository work to external terminal coding agents such as the user's host Claude Code/Codex/Cursor/Gemini CLI or container-installed pal agents.
74
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
3 findings: 2 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Several listed URLs are direct installer script endpoints (curl/PowerShell piped to sh/iex) — a high-risk delivery vector that can run arbitrary code if executed, even when hosted on vendor-like domains; http://localhost:80 is local and not a remote download.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The documentation intentionally includes multiple "bypass" flags that remove agent approvals/permission checks and several remote install pipelines (curl|sh / irm | iex), which together enable unsafe remote code execution and supply-chain/exfiltration risks if abused.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill instructs users to enable Remote Code Execution and explicitly tells them to "Press F3... if the task needs host file writes," which encourages granting the agent host-level write permissions and potentially modifying system files—actions that can compromise the machine state.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill includes runtime install commands that fetch and execute remote scripts (e.g., curl -LsSf https://cli.agent-zero.ai/install.sh | sh and irm https://cli.agent-zero.ai/install.ps1 | iex, plus curl installers at https://cursor.com/install, https://x.ai/cli/install.sh, https://hermes-agent.nousresearch.com/install.sh, and https://opencode.ai/install), which run remote code during skill execution.
- Repository
- agent0ai/agent-zero
- Commit
391fab9
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.