Back to skill

Security audit

project-specification

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward project-specification workflow helper with disclosed document creation and workflow continuation behavior.

Before installing, know that this skill is designed to save a specification file and then move directly into the planning phase unless you use --standalone or explicitly tell it to stop after the specification.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly requires automatic continuation after writing `docs/specification.md`, including invoking `Skill(attune:project-planning)` without confirmation. In an agent setting, this can cause unexpected file modifications and additional workflow execution beyond the user’s immediate request, reducing user control and potentially compounding mistakes or side effects.

Autonomous Decision Making

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

**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
95% confidence
Finding
The instruction to 'Do NOT prompt the user for confirmation' removes an important safety checkpoint before transitioning into a new phase. This is especially risky because the skill is not just generating text; it also assumes successful file creation and then autonomously advances workflow state, which can lead to unintended actions if the specification is incomplete, wrong, or produced in the wrong repository context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.