Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it claims, but users should understand it sends prompts and a token to an external image API and currently documents a less-safe token workflow.
Install only from a source/version you trust, avoid putting long-lived API tokens directly in shell history, and do not submit confidential prompts or reference identifiers unless you are comfortable sharing them with the Neta/TalesOfAI image service.
miniatureworldgenerator.js:9API Token Exposed Through Command-Line Arguments
SKILL.md:31Unpinned Installation Commands Create Supply-Chain Exposure
The documented behavior says the skill uses the Neta API, but the analysis indicates the implementation actually calls a different external service and supports reference-based generation not fully disclosed in the description. This mismatch is dangerous because users may provide prompts, tokens, or images under false assumptions about where data is sent and how it is processed, increasing privacy, trust, and data-handling risk.
The README describes generating images through an external API but does not clearly warn users that their prompts, token, and any reference-image identifiers are transmitted to a third-party service. In a creative skill, prompts may contain sensitive or proprietary ideas, so the lack of an explicit privacy/data-sharing notice can lead to inadvertent disclosure.
The README instructs users to install and run tooling via npx skills without pinning a specific version. That creates a supply-chain risk because users may fetch and execute whatever package/version is current at install time, including a compromised or typosquatted release.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
The skill declares Bash usage and appears to require outbound network access to an external image API, but it does not restrict or declare tool scope with permissions or allowed-tools. That omission increases the attack surface because a consumer cannot easily tell what external actions the skill may perform, and a Bash-based implementation with implicit network capability can be repurposed for unintended exfiltration or arbitrary remote access.
Using npx skills add blammectrappora/miniature-world-generator without a pinned version introduces supply-chain risk because the fetched package can change over time. An attacker who compromises the publisher account or a dependency path could cause users to install a different, potentially malicious version than the one originally reviewed.
This finding points to the hardcoded external destination itself. While contacting an external image API is expected for this skill, the mismatch between the advertised Neta AI service and the actual talesofai.com endpoint creates a supply-chain/trust issue: prompts, reference UUIDs, and authentication material are sent to a different service than users may expect.
};
}
const res = await fetch('https://api.talesofai.com/v3/make_image', {
method: 'POST',
headers: HEADERS,
body: JSON.stringify(body),
This finding points to the hardcoded external destination itself. While contacting an external image API is expected for this skill, the mismatch between the advertised Neta AI service and the actual talesofai.com endpoint creates a supply-chain/trust issue: prompts, reference UUIDs, and authentication material are sent to a different service than users may expect.
};
}
const res = await fetch('https://api.talesofai.com/v3/make_image', {
method: 'POST',
headers: HEADERS,
body: JSON.stringify(body),
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
for (let attempt = 0; attempt < maxAttempts; attempt++) {
await new Promise(r => setTimeout(r, 2000));
const res = await fetch(`https://api.talesofai.com/v1/artifact/task/${taskUuid}`, {
headers: HEADERS,
});
No suspicious patterns detected.