ClawHub
Back to skill

Security audit

krea

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Krea.ai media-generation helper with expected third-party API use and local output saving, though users should treat submitted media and API keys carefully.

Install if you are comfortable using Krea.ai for generation and enhancement. Do not submit secrets, regulated data, private URLs, or confidential media unless Krea's data handling is approved for your use; prefer KREA_API_TOKEN over --api-key to reduce command-line secret exposure; and review downloaded outputs before opening or sharing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
subprocess.run(["notify-send", title, message], timeout=5)
        elif system == "Darwin":
            script = f'display notification "{message}" with title "{title}"'
            subprocess.run(["osascript", "-e", script], timeout=5)
        else:
            print("\a", end="", file=sys.stderr)
    except Exception:
Confidence
79% confidence
Finding
subprocess.run(["osascript", "-e", script], timeout=5)

Tainted flow: 'url' from requests.post (line 529, network input) → requests.get (network output)

Medium
Category
Data Flow
Content
def download_file(url, filename):
    """Download a URL to a local file."""
    os.makedirs(os.path.dirname(filename), exist_ok=True) if os.path.dirname(filename) else None
    r = requests.get(url, stream=True)
    r.raise_for_status()
    with open(filename, "wb") as f:
        for chunk in r.iter_content(chunk_size=8192):
Confidence
88% confidence
Finding
r = requests.get(url, stream=True)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill describes sending prompts, images, videos, and training URLs to Krea.ai and saving outputs locally, but it does not clearly warn users that their content leaves the local environment and may be retained or processed by a third-party service. In a creative-media skill, users may provide sensitive images, proprietary assets, or internal URLs, so omission of a clear disclosure materially increases privacy and data-handling risk.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.