coding-cli
将编码工作委托给 Manager 持有的 AI CLI 工具（Claude Code / Gemini CLI / qodercli）执行
60
71%
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 ./manager/agent/skills-alpha/worker-skills/coding-cli/SKILL.mdSecurity
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
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 skill explicitly instructs uploading entire workspace files (including anything under /root) to an external MinIO storage and delegating execution to a remote Manager/CLI, which creates an intentional remote-code-execution/backdoor and data-exfiltration pathway that can leak sensitive files and allow arbitrary code changes.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow reads outsider-authored free text from the repository/workspace content (e.g., via `git clone <repo-url>` or copying external source into `/root/agentteams-fs/.../workspace`), and that content is then ingested into the Manager’s CLI context when the `coding-request` is sent with `workspace: /root/agentteams-fs/shared/tasks/{task-id}/workspace`.
- Repository
- agentscope-ai/AgentTeams
- Commit
785c2db
- 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.