Minimax Image Gyh

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it claims, but some included scripts silently fall back to a hardcoded MiniMax API key instead of requiring your own key.

Review this skill before installing. If you use it, set your own MINIMAX_API_KEY, avoid sending sensitive prompts, verify output paths, and do not rely on the embedded fallback key; the publisher should remove and rotate that key and declare the credential requirement properly.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

If you run this without your own MiniMax key, your prompts may be sent under an embedded account/key with unclear ownership, billing, audit, and privacy implications.

Why it was flagged

The script embeds a MiniMax API key and silently uses it when MINIMAX_API_KEY is not set, despite the skill description framing the environment variable as the credential mechanism.

Skill content
DEFAULT_API_KEY = "sk-cp-MFXJC1..."; api_key = os.environ.get("MINIMAX_API_KEY") or DEFAULT_API_KEY
Recommendation

Remove and revoke the embedded key, require MINIMAX_API_KEY explicitly, and declare that credential in the skill metadata before use.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

Prompts are shared with MiniMax, and generated images can overwrite or add files wherever the output path points.

Why it was flagged

The script sends the user prompt to the MiniMax API and writes the returned image to a caller-specified path; this is expected for the skill but is still network and file-mutation behavior.

Skill content
resp = requests.post(url, headers=HEADERS, json=payload, timeout=60) ... with open(path, "wb") as f: f.write(resp.content)
Recommendation

Avoid sensitive prompts, confirm the output path before running, and use the skill only when image generation is intended.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Users may need to install an external Python package that is not pinned or installed through a reviewed install spec.

Why it was flagged

The skill asks for a manual, unpinned Python package install while the provided install specification is absent; this is a disclosed setup step but not fully managed by metadata.

Skill content
- `pip3 install requests`
Recommendation

Install dependencies only from trusted package sources, and prefer a publisher-provided pinned requirements file or install spec.