Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a normal image-generation skill, but it sends your prompt and API token to the named Neta/TalesOfAI service and should handle tokens and install commands more safely.
Install from a trusted source, avoid placing a real API token directly in shell history when possible, rotate the token if you already exposed it, and do not send sensitive personal photos, names, or identifying prompts unless you are comfortable sharing them with the Neta/TalesOfAI service.
snapchatfilterartgenerator.js:15API Token Exposed Through Command-Line Arguments
SKILL.md:31Unpinned Third-Party Package Execution Through npx Installation Instructions
The README instructs users to install the skill via npx skills add ... without pinning a specific version of the tool or package. This creates a supply-chain risk because users may fetch whatever version is current at execution time, which could include a compromised or unexpected release if the upstream package or distribution path is tampered with.
The skill advertises only the Bash tool and does not declare any explicit tool scope or permissions, yet its documented behavior requires outbound network access to the Neta API. That mismatch can cause reviewers and users to underestimate what the skill can do, weakening least-privilege controls and increasing the risk of unintended data exfiltration or unauthorized external calls.
The install instruction uses npx skills without pinning a specific version, which makes installs depend on whatever package version is current at execution time. This creates a supply-chain risk: a malicious or compromised upstream release could change behavior, introduce unsafe code, or alter transitive dependencies without the user noticing.
This code performs an outbound POST to a third-party image-generation endpoint and includes the user's token, prompt, and image-generation parameters. External transmission is expected for this skill's functionality, but it is still a genuine security/privacy concern because potentially sensitive user content and authentication material are disclosed to an outside service.
let createRes;
try {
createRes = await fetch('https://api.talesofai.com/v3/make_image', {
method: 'POST',
headers,
body: JSON.stringify(body),
This code performs an outbound POST to a third-party image-generation endpoint and includes the user's token, prompt, and image-generation parameters. External transmission is expected for this skill's functionality, but it is still a genuine security/privacy concern because potentially sensitive user content and authentication material are disclosed to an outside service.
let createRes;
try {
createRes = await fetch('https://api.talesofai.com/v3/make_image', {
method: 'POST',
headers,
body: JSON.stringify(body),
The polling request sends the authentication token and task identifier to the same third-party service to retrieve job results. This is part of normal operation, but it still constitutes external transmission of metadata and credentials to a remote provider, which matters in a tool dealing with personal image generation requests.
let pollRes;
try {
pollRes = await fetch(`https://api.talesofai.com/v1/artifact/task/${taskUuid}`, {
method: 'GET',
headers,
});
The script sends user-supplied prompt text and an optional reference image identifier to a third-party API, but it gives users only a generic submission message and no clear privacy notice about what data leaves the local environment. In a skill that may be used with personal selfies and identifying prompts, this creates a real privacy risk because users may unknowingly transmit sensitive content to an external service.
No suspicious patterns detected.