Runware Image & Video generation

PassAudited by ClawScan on May 1, 2026.

Overview

The skill appears to match its Runware media-generation purpose, but it needs a Runware API key and sends prompts or selected input images to Runware.

This looks like a normal Runware media-generation skill. Before installing, be aware that it needs a Runware API key, may incur Runware usage costs, and sends prompts or selected images to Runware; avoid using sensitive media unless that data sharing is acceptable.

Findings (3)

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.

What this means

Using the skill gives the scripts access to a Runware account credential and may consume Runware credits for generated media.

Why it was flagged

The skill requires a Runware credential to make API calls. This is expected for the service, but it is noteworthy because the registry metadata declares no required environment variables or primary credential.

Skill content
Set `RUNWARE_API_KEY` environment variable, or pass `--api-key` to scripts.
Recommendation

Only provide a Runware API key you intend to use with this skill, prefer an environment variable over command-line arguments, and monitor Runware usage or billing.

What this means

Prompts and any input images used for transformations or video generation may be transmitted to Runware's API.

Why it was flagged

The script sends generation tasks to Runware and can encode local input images for image-to-video requests. This is purpose-aligned, but users should recognize that selected image content leaves the local machine.

Skill content
url = "https://api.runware.ai/v1" ... with open(path, "rb") as f:
        b64 = base64.b64encode(f.read()).decode("utf-8")
Recommendation

Do not use private or sensitive images or prompts unless you are comfortable sending them to Runware and have reviewed Runware's privacy and retention terms.

What this means

There is less publisher and provenance information available for deciding whether to trust the skill.

Why it was flagged

The artifact metadata does not identify a source repository or homepage. The included code is visible and no remote install is specified, so this is a provenance note rather than evidence of malicious behavior.

Skill content
Source: unknown
Homepage: none
Recommendation

Review the included scripts before use and prefer installing skills from publishers or repositories you trust.