Tetra Scar Safety

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:26 PM UTC
• Version:
  0.1.0

Overview

This is a local security scanning skill whose file scanning and incident memory are disclosed and aligned with its stated safety purpose.

Reasonable to install for local safety checks. Run audits only on directories you intend to inspect, avoid recording real secrets in incident text, and periodically review or protect safety_scars.jsonl because its contents influence future allow/block decisions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill documentation indicates capabilities to read environment variables, read/write files, and invoke shell commands, but it declares no permissions. That mismatch can mislead operators and policy engines, causing the skill to be granted more trust than warranted and enabling sensitive operations without explicit review.

Context-Inappropriate Capability

Medium

• Confidence: 84% confidence
• Finding: The audit() function can recursively inspect arbitrary local directories and read file contents, including sensitive files such as .env and credential-like filenames, with no path restrictions, consent checks, or allowlist. In an agent environment, this broad read capability can expose secrets or proprietary data if another component invokes audit on a sensitive path.

VirusTotal

64/64 vendors flagged this skill as clean.