Back to skill

Security audit

exam-stress-coach

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent local exam-stress helper, but users should know it can save stress notes and plans as local files.

Install only if you are comfortable with stress levels and optional notes being saved locally in JSON files. Avoid putting highly sensitive details in notes on shared or backed-up machines, and be careful with the plan --output path because it writes to the path you provide.

SkillSpector

By NVIDIA
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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill documentation describes persistent file-writing behavior (`stress_coach.py log` appends to `stress_log.json`, and `plan --output` writes a JSON file) while the skill declares no permissions. This mismatch is a real security/design issue because undeclared write capability can violate least-privilege expectations, surprise users or hosting platforms, and create opportunities for unintended data persistence or file overwrite if the implementation is not constrained.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script stores user-provided stress levels and free-form notes in a local JSON file without any disclosure, consent, or privacy warning. Because this data concerns mental health and may include sensitive personal details, silent persistence can expose users to unintended disclosure through shared accounts, backups, or other local access.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.