ClawHub
Back to skill

Security audit

project-planning

Security checks across malware telemetry and agentic risk

Overview

The skill is a planning aid, but it explicitly chains into an execution phase without asking the user first.

Review this skill before installing if you expect planning to stop after producing a plan. Use `--standalone` or explicitly tell the agent to stop after planning, because the skill otherwise instructs the agent to proceed directly into the execution phase.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly requires automatic transition into the execution phase immediately after creating the implementation plan, without an explicit user confirmation step. In an agent setting, this changes the workflow from planning into action-taking and can cause unintended execution, file changes, or external side effects beyond the user's last clearly expressed intent.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- `docs/implementation-plan.md` does not exist or is empty (phase failed)
- User explicitly requests to stop after planning

**Do NOT prompt the user for confirmation** — this is a lightweight checkpoint, not an interactive gate. The user can always interrupt if needed.

## Related Skills
Confidence
97% confidence
Finding
Do NOT prompt the user

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.