ClawHub
Back to skill

Security audit

Deep Infra

Security checks across malware telemetry and agentic risk

Overview

This appears to be a DeepInfra model-routing skill whose external API use and local notes are aligned with its stated purpose, though users should understand prompts leave their machine.

Install only if you are comfortable sending selected prompts to DeepInfra for inference. Do not include API keys, passwords, personal records, or regulated data in prompts, and periodically review the local ~/deep-infra/memory.md file if you use the skill's persistent notes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to keep compact notes in `~/deep-infra/memory.md` without requiring user knowledge, consent, or a clear disclosure that persistent data will be written to the user's home directory. This creates a privacy and safety risk because routing preferences, budget ceilings, incidents, and provider details may be stored beyond the current session and could later be exposed, misused, or become stale and misleading.

External Transmission

Medium
Category
Data Exfiltration
Content
| Endpoint | Data Sent | Purpose |
|----------|-----------|---------|
| https://api.deepinfra.com/v1/openai/models | none or auth header | Discover current model catalog and metadata |
| https://api.deepinfra.com/v1/openai/chat/completions | user prompt content and selected model id | Execute routed inference requests |

No other data is sent externally.
Confidence
92% confidence
Finding
https://api.deepinfra.com/

External Transmission

Medium
Category
Data Exfiltration
Content
| Endpoint | Data Sent | Purpose |
|----------|-----------|---------|
| https://api.deepinfra.com/v1/openai/models | none or auth header | Discover current model catalog and metadata |
| https://api.deepinfra.com/v1/openai/chat/completions | user prompt content and selected model id | Execute routed inference requests |

No other data is sent externally.
Confidence
97% confidence
Finding
https://api.deepinfra.com/

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.