ClawHub
Back to skill

Security audit

sn-image-doctor

Security checks across malware telemetry and agentic risk

Overview

This SenseNova environment doctor is mostly purpose-aligned, but it should be reviewed because it can print resolved configuration values that may include API keys or endpoints.

Install only if you are comfortable with a diagnostic tool reading local SenseNova project files and environment-derived configuration. Avoid running it in shared terminals, CI logs, support sessions, or screen shares unless the config printer is removed or confirmed to redact API keys and tokens.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
81% confidence
Finding
The skill documentation describes capabilities to read environment state and project files, but no explicit permissions are declared. In agent ecosystems, missing permission declarations weaken user awareness and policy enforcement, allowing a diagnostic skill to access sensitive configuration data without clear consent boundaries.

Tp4

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding
A diagnostic skill that also prints resolved configuration values or enumerates installed skills exceeds the stated purpose and can disclose sensitive operational details. Resolved configuration output may expose secrets or internal endpoints, and skill enumeration can aid reconnaissance for later abuse.

Vague Triggers

Medium
Confidence
77% confidence
Finding
Broad triggers like 'environment check' and 'health check' may invoke this skill unintentionally during unrelated conversations. Because the skill can inspect environment state and prompt for secrets to be saved into .env, accidental activation increases the chance of unnecessary sensitive-data handling.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script prints fully resolved configuration values via `to_string()`/`str(global_configs)` during an environment diagnostic run, and those configs are likely sourced from environment variables such as API keys or service endpoints. This can disclose secrets to terminal output, logs, CI job logs, shell history capture tools, or remote support sessions, especially because a diagnostic tool is likely to be run in shared troubleshooting contexts.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.