Multica Sdd Workflow

• Outcome: Review
• Latest audit: Jun 7, 2026 at 4:47 PM UTC
• Version:
  1.0.0

Overview

The skill is a coherent Multica SDD workflow, but its broad trigger phrases can activate state-changing multi-agent and project-management actions without an explicit confirmation gate.

Install only if you intentionally want generic feature-planning requests to route into a Multica SDD workflow. Before using it, narrow the trigger wording or require explicit confirmation before creating or assigning Multica issues, editing specs/CLAUDE.md/.multica/squad.md, or making git commits.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger phrases are broad, generic project-management terms such as '新建任务', '新增功能', and '功能更新', which can cause the skill to activate in many ordinary conversations unrelated to this high-impact workflow. Because the skill can drive shell commands, issue creation, and state-changing project actions, overbroad invocation increases the risk of unintended execution and unsafe automation in the wrong context.

VirusTotal

64/64 vendors flagged this skill as clean.