ClawHub
Back to skill

Security audit

vet-translator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed veterinary note and lab-result explainer with a local helper script and no evidence of hidden data access, persistence, network use, or destructive behavior.

Reasonable to install for educational help interpreting pet records. Treat outputs as organization and explanation only, verify medical decisions with a veterinarian, and avoid pasting more personal information than needed.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
81% confidence
Finding
The skill instructs the agent to invoke local shell commands such as `python3 scripts/vet_translator.py ...`, but the manifest shown in SKILL.md does not declare any corresponding permissions or execution constraints. Undeclared shell capability is dangerous because it creates a mismatch between what reviewers expect and what the skill can cause an agent to do, increasing the risk of unintended command execution, unsafe argument handling, or privilege creep if user-supplied note text is passed into commands.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical
Code
suspicious.dynamic_code_execution
Location
scripts/test_vet_translator.py:11