pm-requirement-flow

Security checks across malware telemetry and agentic risk

Overview

This is a transparent PM workflow skill, but it can hand work to a separate local dispatch tool that should be reviewed before use.

Install only if you are comfortable with the separate claude-code-dispatch dependency. Before dispatching work, inspect its dispatch.sh script, keep --workdir limited to the intended project, and remove or avoid --permission-mode bypassPermissions if you want manual approval for tool actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

High
Confidence
94% confidence
Finding
The trigger phrases are extremely broad (e.g. '需求', '开发', '开始项目') and can match ordinary conversation, causing the skill to activate in contexts where the user did not explicitly request this workflow. Because the skill includes dispatching work to another tool and recommends non-interactive execution, unintended activation increases the chance of unauthorized or unsafe task delegation.

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal