kreadoai-skills

Security checks across static analysis, malware telemetry, and agentic risk

Overview

The code mostly matches the KreadoAI integration purpose, but its official-source/provenance metadata is inconsistent while it asks for a paid API token.

Before installing, verify that this package really comes from KreadoAI despite the metadata mismatch. If you proceed, use a revocable token, keep the local credential file protected, and confirm any paid media-generation or removal task before allowing the agent to run it.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

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.

What this means

A user may configure a KreadoAI token for a package whose publisher/version lineage is unclear.

Why it was flagged

The packaged metadata conflicts with the provided registry metadata, which lists a different owner ID, slug, and version. Because the skill handles a paid API token, this provenance mismatch is material.

Skill content
"ownerId": "kn7bczybw3dwrwf452ghdtzty582nxj0", "slug": "kreadoai", "version": "1.1.0"
Recommendation

Verify the publisher and package source against KreadoAI's official channels before configuring a token, and prefer a revocable or least-privilege token if available.

What this means

The 'Official' wording could cause users to over-trust the skill with account credentials or paid API actions.

Why it was flagged

The artifact makes an 'Official' authority claim, while the supplied metadata says the source is unknown and the packaged metadata does not match the registry metadata.

Skill content
description: Official KreadoAI Skill.
Recommendation

Treat the official claim as unverified unless confirmed by KreadoAI, and do not enter credentials until provenance is clear.

What this means

Anyone with access to the stored token may be able to use the KreadoAI account and consume paid resources.

Why it was flagged

The skill reads a KreadoAI API token from an environment variable or local credential file and can also write that token during configuration.

Skill content
1. 环境变量 KREADO_API_TOKEN ... 2. ~/.config/kreado/.credentials 文件中存储的 apiToken
Recommendation

Protect the credential file, avoid sharing logs or terminals containing tokens, and revoke or rotate the token if the publisher cannot be verified.

What this means

If invoked unintentionally, the skill could create tasks that cost account credits and process the submitted media URLs.

Why it was flagged

The documented API actions can submit generation/removal jobs that consume paid K-Coin balance; this is purpose-aligned but financially impactful.

Skill content
K-Coin 计费:精品数字人 1/秒,臻品 2/秒,照片 1/秒,TTS 0.3/秒,字幕去除 1/秒。
Recommendation

Require clear user confirmation before running submit/upload/synthesize/removal commands, especially with --wait or production media.