autonomous-loops
自主运行 Claude Code 循环的模式与架构 —— 从简单的顺序流水线到 RFC 驱动的多智能体 DAG 系统。
57
67%
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
Fix and improve this skill with Tessl
tessl review fix ./skills/autonomous-loops/SKILL.mdSecurity
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
This is a raw GitHub-hosted shell script that the skill explicitly instructs users to execute via "curl ... | bash"—a high-risk pattern because it runs arbitrary remote code and can be used to distribute malware.
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
This skill doc intentionally describes sending repository/CI/context data to an external LLM, automating commits/merges, and recommends piping a remote installer into bash — presenting clear data-exfiltration and supply‑chain / remote‑execution risks.
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
This skill instructs an agent to run shell scripts that modify the repository and local filesystem (commit, push, create branches/worktrees, persist session files), to auto-run CI-fixing flows using gh, and even to curl|bash an external install script—enabling arbitrary code execution and persistent state changes on the host (though it does not request sudo or modify system config files explicitly).
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 a runtime installation command that fetches and pipes a remote script to bash (https://raw.githubusercontent.com/AnandChowdhary/continuous-claude/HEAD/install.sh), which executes remote code and thus directly controls behavior at runtime.
- Repository
- xu-xiang/everything-claude-code-zh
- Commit
dfbf946
- 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.