ClawHub

Context Product Manager

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only planning skill that reads relevant project files to produce product plans and coding-agent handoffs, with no install scripts or hidden execution behavior.

Before installing, confirm you are comfortable with the agent reading relevant workspace files when preparing repo-aware plans, and with Chinese being the default conversational language. Review any generated handoff before giving it to another automated coding agent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The invocation description is extremely broad and overlaps with ordinary planning, brainstorming, and coding-prep requests, which can cause the skill to activate in situations the user did not specifically intend. In a delegation/orchestration skill, unintended activation can steer workflows, alter response style, and unnecessarily expose repo-context gathering behavior across a wide set of benign prompts.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill hard-codes communication in Chinese without checking the user's language preference, which can override user intent and degrade transparency, comprehension, and reviewability. In a PM/context-engineering skill that produces specs and agent handoffs, forced language selection can cause misunderstandings in requirements, approvals, and downstream execution.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal