ClawHub
Back to skill

Security audit

Quick Img V2

Security checks across malware telemetry and agentic risk

Overview

This skill is a small curl-based image generator with an optional IP-check helper; its main behavior is visible, but users should be aware it contacts external services.

Install only if you are comfortable with Bash commands that contact SkillBoss and with SkillBoss receiving your prompt and API key. Use a limited or revocable API key, avoid sensitive prompts unless you trust that service, and do not run the Check IP helper unless you want httpbin.org to see your public IP.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Description-Behavior Mismatch

Medium
Confidence
97% confidence
Finding
The documented 'Check IP' behavior is unrelated to the skill's stated purpose of image generation, which creates unnecessary capability and increases suspicion of hidden network/environment inspection. Even if implemented locally via a bundled script, this mismatch can expose host network metadata or normalize running commands users would not expect from the skill description.

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
IP-checking or network-inspection behavior is unjustified in an image-generation skill and may reveal system or network information unrelated to the user's task. This kind of capability broadens the attack surface and can be abused for environment reconnaissance before further exfiltration or targeting.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The script behavior does not match the declared skill purpose: instead of generating images via curl and the SkillBoss API, it makes an unrelated request to httpbin.org and prints the caller's public IP-related origin data. This creates unnecessary external data exposure and is suspicious because it introduces undisclosed network behavior unrelated to the advertised functionality.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The example instructs users to send both their API key and prompt content to an external service without any warning about third-party transmission, logging, or privacy implications. Users may unknowingly transmit sensitive prompts or credentials to a remote endpoint under the assumption that the skill is purely local tooling.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script performs an outbound network request without any user-facing notice, consent, or justification in the skill behavior. Even though the request is a simple GET, it leaks environment-associated metadata such as the caller's IP to a third party and normalizes hidden network activity in a skill that is supposed to do something else.

External Transmission

Medium
Category
Data Exfiltration
Content
## Generate

```bash
curl -s -X POST https://api.heybossai.com/v1/run \
  -H "Content-Type: application/json" \
  -d "{\"api_key\":\"$SKILLBOSS_API_KEY\",\"model\":\"mm/img\",\"inputs\":{\"prompt\":\"A sunset\"}}" \
  | node -e "let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{const j=JSON.parse(d);console.log(j.image_url||JSON.stringify(j))})"
Confidence
92% confidence
Finding
https://api.heybossai.com/

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.