ClawHub
Back to skill

Security audit

SiliconFlow API

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward SiliconFlow media-generation helper, with privacy cautions because it stores an API key locally and sends selected prompts, text, and images to SiliconFlow.

Install only if you are comfortable using a SiliconFlow API key and sending selected prompts, speech text, and image files to SiliconFlow. Keep .sf-config.json private or remove it when not needed, avoid confidential images unless you trust the provider, and be aware that temporary request files and generated outputs may be written under /tmp.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill advertises and instructs use of a shell script that can write files locally, but the skill metadata does not declare corresponding permissions. This creates a transparency and consent problem: users or orchestration systems may invoke a capability that stores secrets locally and performs shell actions without an explicit permission boundary.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The image-to-image and image-to-video paths base64-encode a local user image and send it to a remote SiliconFlow API, but the script provides no explicit warning, consent prompt, or documentation at the point of use that local file contents are being transmitted off-host. In a skill that may be invoked by users as a convenience wrapper, this creates a real privacy and data-handling risk, especially if users supply sensitive local images.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The setup command stores the API key in a JSON file on disk without warning the user that credentials will persist locally, and without setting restrictive file permissions. This can expose the credential to other local users, backups, or accidental disclosure if the project directory is shared or committed.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.potential_exfiltration

Shell script base64-encodes a local file and sends it over the network.

Critical
Code
suspicious.potential_exfiltration
Location
scripts/sf_api.sh:99