T08 · Insecure Dependencies
- Location
SKILL.md:32- Finding
Unpinned Remote Package Execution in Installation Instructions
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent image generator, but it uses an API token and broad shell execution with under-scoped install and credential-handling instructions that users should review before installing.
Install only if you are comfortable sending prompts, reference image IDs, and a Neta token to the external image service. Prefer a pinned or ClawHub-managed install path, avoid putting real tokens in shell history or logs, and rotate any token already used in command-line examples.
SKILL.md:32Unpinned Remote Package Execution in Installation Instructions
gothicportraitgenerator.js:3API Token Exposed Through Command-Line Arguments
The README clearly instructs users to send prompts and optional reference-image identifiers to a third-party image-generation API, but it does not warn that user content will leave the local environment or discuss privacy, retention, or handling by the external service. This can lead users to unknowingly transmit sensitive personal, proprietary, or biometric-related content to an external provider. The skill context increases the concern because portrait generation and reference-image use can involve identifiable people and stylistic source material.
The README instructs users to install or invoke the skill via npx skills without pinning a specific package version. That exposes users to supply-chain risk because a newly published or compromised package version could be fetched and executed at install time. In the context of an agent skill, this is more dangerous because users are likely to copy-paste the command directly and execute remote code immediately.
The skill declares tools: Bash and documents use of an external API token plus a Node-based invocation, but it does not define any permissions or allowed-tools scope despite requiring network access. This can cause the agent runtime to grant broader-than-necessary capabilities or leave network use insufficiently constrained, increasing the risk of unintended external requests and token exposure.
Line L20 says to use the skill when someone asks to "generate or create gothic portrait generator images," which is awkward and underspecified as an activation condition. It does not clearly bound the trigger phrases or provide exclusion examples, increasing the chance of unintended invocation from broadly similar image-generation requests.
The install instruction uses npx skills add omactiengartelle/gothic-portrait-generator without pinning a specific version. This makes installs non-reproducible and exposes users to supply-chain risk if the package or dependency resolution changes, is hijacked, or a malicious update is published later.
The code hardcodes an outbound HTTPS destination to api.talesofai.com while the skill metadata and token acquisition instructions reference neta.art, creating a vendor-mismatch red flag. That mismatch makes the external transmission more dangerous because users may believe they are authorizing one service while their prompt data and token are actually sent to another.
async function main() {
// Submit the image generation task
const createRes = await fetch("https://api.talesofai.com/v3/make_image", {
method: "POST",
headers,
body: JSON.stringify(body),
The code hardcodes an outbound HTTPS destination to api.talesofai.com while the skill metadata and token acquisition instructions reference neta.art, creating a vendor-mismatch red flag. That mismatch makes the external transmission more dangerous because users may believe they are authorizing one service while their prompt data and token are actually sent to another.
async function main() {
// Submit the image generation task
const createRes = await fetch("https://api.talesofai.com/v3/make_image", {
method: "POST",
headers,
body: JSON.stringify(body),
The polling request repeatedly contacts the same third-party service and sends the authentication header on each attempt. While this is functionally part of asynchronous job handling, it expands credential exposure and network dependency, and in combination with the provider/domain mismatch it increases the blast radius if the remote service is untrusted or compromised.
for (let attempt = 0; attempt < 90; attempt++) {
await new Promise(resolve => setTimeout(resolve, 2000));
const pollRes = await fetch(`https://api.talesofai.com/v1/artifact/task/${taskUuid}`, {
headers,
});