Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward external image-generation helper, with some credential-handling and install-hygiene issues users should understand before use.
Use this only with prompts you are comfortable sending to Neta/talesofai.com. Prefer a limited-scope or disposable Neta token, be aware that the documented --token usage can expose the token in process listings or logs, and install from a pinned reviewed version when possible.
blogimageclaw.js:10API Token Exposed Through Command-Line Arguments
SKILL.md:32Unpinned Third-Party Skill Installation
The static analysis indicates the documented purpose does not fully match actual behavior, including use of a different external service/API, authentication-token handling, and an execution interface not transparently declared. This mismatch is dangerous because it prevents informed consent, obscures where user data and credentials are sent, and can hide unexpected behavior behind a benign-seeming description.
The README instructs users to install and run tooling via npx skills without pinning a specific version. This can cause users to fetch and execute whatever package version is current at install time, creating a supply-chain risk if the package is compromised or a breaking/malicious version is published.
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 documents use of a Bash/Node command that calls an external API and requires a bearer token, but it does not declare any tool scope or permissions. This is dangerous because users and host systems are not clearly informed that the skill has network-capable behavior and may transmit prompts or secrets to a third party.
The skill description omits a warning that user prompts are sent to an external image-generation API. In this context, that omission is significant because users may enter proprietary, personal, or sensitive text under the assumption processing is local, resulting in unintended third-party disclosure.
The invocation guidance says to use the skill whenever someone asks to generate images, without clear limits, consent checks, or disclosure that content will be sent externally. Broad trigger phrasing can cause over-invocation, accidental transmission of sensitive prompts, or use in contexts where users did not intend a third-party API call.
The install instruction uses npx skills add BarbaraLedbettergq/blog-image-claw-skill without pinning a version or immutable reference. This can lead to supply-chain risk if the package or referenced content changes later, causing users to install unexpected or malicious updates.
This POST request exfiltrates user-provided content and a credential-bearing header to an external domain. While external API calls are expected for an image-generation skill, the security concern is that sensitive prompts or reused tokens may be transmitted off-box without clear trust boundaries or validation of user intent.
// --- Submit image generation job ---
async function makeImage() {
const res = await fetch("https://api.talesofai.com/v3/make_image", {
method: "POST",
headers: HEADERS,
body: JSON.stringify(body),
This POST request exfiltrates user-provided content and a credential-bearing header to an external domain. While external API calls are expected for an image-generation skill, the security concern is that sensitive prompts or reused tokens may be transmitted off-box without clear trust boundaries or validation of user intent.
// --- Submit image generation job ---
async function makeImage() {
const res = await fetch("https://api.talesofai.com/v3/make_image", {
method: "POST",
headers: HEADERS,
body: JSON.stringify(body),
The skill sends a user-supplied token in the x-token header to a third-party API and also transmits the prompt/body externally, but it provides no user-facing disclosure beyond requiring a token. In an agent-skill context, silent external transmission of credentials and content is risky because users may not realize their token and prompt are leaving the local environment and being processed by an external service.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
// --- Poll for result ---
async function pollTask(taskUuid) {
const url = `https://api.talesofai.com/v1/artifact/task/${taskUuid}`;
const MAX_ATTEMPTS = 90;
const INTERVAL_MS = 2000;
This script sends both the user-supplied prompt and an authentication token to a third-party API endpoint, but the code provides no explicit notice, consent flow, or data-minimization safeguards. In an agent setting, prompts may contain sensitive draft content, internal business data, or personal information, so silent transmission to an external service creates a real confidentiality and privacy risk.
No suspicious patterns detected.