v1.0.0

Ai Media Cli

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:13 AM.

Analysis

This appears to be a coherent setup and usage guide for an external AI media CLI, with expected but important handling of an API key, paid credits, and package installation.

GuidanceBefore installing, verify the ai-media-generator package and only configure a dedicated, revocable API key. Leave AI_MEDIA_BASE_URL unset unless you intentionally trust a specific endpoint, and approve any commands that spend credits or submit prompts/images to the service.

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityMediumConfidenceHighStatusNote

SKILL.md

install -> recharge credits -> create API key -> set key -> config show -> models list --json -> run first image/video task

The documented workflow includes account funding and running media-generation jobs, which are expected for this CLI but can spend credits or send prompts to the service.

User impactIf the agent runs generation commands or guides payment steps without your review, it could consume paid credits or submit content you did not intend to send.

RecommendationApprove any recharge, subscription, or media-generation command explicitly, and review prompts, reference images, model choices, and wait/polling options before execution.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceMediumStatusNote

install spec

node | package: ai-media-generator | creates binaries: ai-media

The skill installs an external package that provides a local CLI binary. That is central to the skill’s stated purpose, but the artifact review does not include the package contents.

User impactInstalling the package gives the external CLI code the ability to run on your machine under your user account.

RecommendationInstall only from the intended package registry/source, verify the package name and publisher, and consider pinning or reviewing the package before global installation.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityMediumConfidenceHighStatusNote

references/platform-onboarding.md

create API key -> copy plaintext key now -> ai-media config set-key ...

The skill instructs users to handle a plaintext API key and configure it for the CLI, which is purpose-aligned but grants access to the user’s ricebowl.ai account.

User impactAnyone who obtains the API key may be able to use the account’s media-generation credits or access service capabilities tied to that key.

RecommendationUse a dedicated, revocable API key for this CLI, avoid pasting real keys into chat or logs, and avoid sharing config output if it may include secrets.