Openai Image Gen 1.0.1

ReviewAudited by ClawScan on May 10, 2026.

Overview

This image-generation skill mostly matches its purpose, but it needs review because user prompt text is written directly into an HTML gallery that users are told to open.

Only install after reviewing the gallery-generation behavior. Use a dedicated OpenAI API key, check OPENAI_BASE_URL/OPENAI_API_BASE before running, and avoid opening generated index.html files created from untrusted prompts until the skill escapes prompt text safely.

Findings (4)

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.

Medium

#ASI05: Unexpected Code Execution

What this means

A crafted prompt could make the generated gallery run script in the user's browser when they open index.html.

Why it was flagged

The script accepts user-supplied prompts and writes them directly into index.html without HTML escaping. If a prompt contains HTML or JavaScript, opening the generated gallery could execute unexpected browser code.

Skill content

p.add_argument("--prompt", action="append", default=None, help="repeatable; overrides random prompts") ... html.append(f"<pre>{it['prompt']}</pre>")

Recommendation

Escape prompt text before writing it into HTML, for example with html.escape(), or render prompt text through a safe templating mechanism.

Low

#ASI03: Identity and Privilege Abuse

What this means

The user's OpenAI key will be used to make paid API requests and authorize image generation.

Why it was flagged

The skill uses an OpenAI API key as a bearer token, which is expected for its purpose. The registry metadata, however, declares no required env vars or primary credential, so the credential requirement is under-declared outside SKILL.md.

Skill content

api_key = args.api_key or os.environ.get("OPENAI_API_KEY") ... "Authorization": f"Bearer {api_key}"

Recommendation

Declare OPENAI_API_KEY in the skill metadata and advise users to use a scoped key, avoid passing keys on the command line when possible, and monitor usage.

Low

#ASI03: Identity and Privilege Abuse

What this means

If OPENAI_BASE_URL or OPENAI_API_BASE is set to a third-party endpoint, the API key and prompts may be sent there instead of directly to OpenAI.

Why it was flagged

The script can send requests, prompts, and the bearer token to an environment-configured OpenAI-compatible base URL. This is a common integration feature, but it is not disclosed in SKILL.md.

Skill content

os.environ.get("OPENAI_BASE_URL") or os.environ.get("OPENAI_API_BASE") or "https://api.openai.com"

Recommendation

Document the base-URL override and tell users to check these environment variables before running the skill.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

It may be harder to verify exactly which package, publisher, or version is being reviewed.

Why it was flagged

The bundled metadata does not match the provided registry metadata, which lists a different owner ID, slug, and version. This does not show malicious behavior, but it is a provenance and packaging consistency gap.

Skill content

"ownerId": "kn70pywhg0fyz996kpa8xj89s57yhv26", "slug": "openai-image-gen", "version": "1.0.1"

Recommendation

Confirm the publisher and version before installing, and align registry metadata with the bundled _meta.json.