compose:brainstorm
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Security
2 findings: 2 critical severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions.
What this means
Detected 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.
Why it was flagged
The prompt claims a strict HARD-GATE requiring design presentation and user approval before any implementation, but contains multiple explicit "Autonomous override" clauses that allow skipping design/approval and proceeding directly to implementation when "no user is available," which contradicts and covertly undermines the skill's stated safety gate.
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 includes explicit "Autonomous override" rules that intentionally bypass user approval/design gates and permit the agent to proceed to implementation when "no user is available," which functions as a built-in backdoor enabling actions without user consent.
- Repository
- XiaomiMiMo/MiMo-Code
- Commit
ec3f989
- 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.