AIML Generate images and videos

• Outcome: Review
• Latest audit: May 28, 2026, 12:24 PM
• Version:
  1.0.2

Overview

This is a normal AIMLAPI media-generation skill, but one image-input option can upload any local file path it is given, not just images.

Install only if you are comfortable sending prompts and selected media to AIMLAPI. Do not pass private files, credentials, SSH keys, browser profiles, or other non-image paths to --image-url or --apikey-file; prefer AIMLAPI_API_KEY and only use image files you intentionally want to upload.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Taint Tracking: Direct Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Tainted flow: 'req' from os.getenv (line 64, credential/environment) → urllib.request.urlopen (network output)

Critical

• Category: Data Flow

Content

url_value = item.get("url")
        file_path = out_dir / f"image-{int(time.time())}-{index}.png"
        req = urllib.request.Request(url_value, headers={"User-Agent": args.user_agent})
        with urllib.request.urlopen(req) as res:
            file_path.write_bytes(res.read())
    print(f"SUCCESS: {out_dir}")

• Confidence: 82% confidence
• Finding: with urllib.request.urlopen(req) as res:

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill declares access to an API key in `env` and instructs use of local scripts that perform network requests and write output files, but it does not declare corresponding permissions. This creates a trust and governance gap: a caller may believe the skill is low-privilege when it can actually read secrets, contact external services, and write data locally.

VirusTotal

64/64 vendors flagged this skill as clean.