Execute AI coding CLI tools (Claude Code / Gemini CLI / qodercli / Qwen Code / OpenCode) on behalf of Workers. Use when a Worker sends a coding-request: message, asking the delegating agent (Manager, team Leader, or an authorized Worker) to run coding operations in their workspace.
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./manager/agent/skills/coding-cli-management/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill openly documents unattended, auto-approving runners, and its only arguably sketchy content is guidance on reframing a governed runner's refused injected request so the runner complies, which is a risky practice toward the user but not shown to be malicious.
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.
The skill does not request sudo, create accounts, or edit system, SSH, or service files; it mainly writes the user's own config and installs CLIs via npm into a user prefix, which the rules treat as benign. It does, however, default the agent to running auto-approve `--yolo` / `--auto` runs as the delegating agent with its credentials and sockets, which is a bypass of approval controls, so I flag it at moderate severity.
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.
The required workflow runs the CLI on a Worker-authored `coding-request:` prompt against a task workspace the Worker prepares, which could include externally fetched code or docs the Worker chose to pull in, so outsider text is reachable only through the Worker's selection rather than forced delivery.
agentscope-ai/AgentTeams
bc2c064
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.