Security audit
Security checks for vulnerabilities and agentic risk
This storyboard skill is mostly coherent, but it tells users to execute mutable remote installation code and unpinned package commands, which warrants manual review before installation.
Review this skill before installing. Use the storyboard guidance freely, but do not run the curl-to-shell installer or unpinned npx commands in an environment with sensitive files or credentials unless you independently trust and verify the sources. Treat prompts, scripts, shot lists, and image filenames used with infsh as potentially sent to a third-party service.
SKILL.md:14Remote Installer Is Downloaded and Executed Without Independent Verification
SKILL.md:259Unpinned Packages and Skill Sources Are Installed Through npx
curl ... | sh fetches and immediately executes a remote script, which is a classic high-risk supply-chain pattern because any compromise of the distribution endpoint, DNS, TLS termination, or upstream publishing process can lead to arbitrary code execution on the host. The risk is amplified here because the skill is framed as a benign storyboard aid, making users more likely to run the command without the scrutiny they would apply to a software-installation skill.
curl -fsSL https://cli.inference.sh | sh && infsh login
# Generate a storyboard panel
infsh app run falai/flux-dev-lora --input '{
The manifest presents the skill as storyboard knowledge and planning, but the content materially expands into remote AI image generation and image stitching through an external CLI. That mismatch can cause agents or users to grant broader execution and data-sharing capabilities than expected, increasing the chance of unsafe tool use under a seemingly innocuous creative-planning label.
The manifest description lists triggers such as "storyboard," "film planning," "video planning," and "scene planning" without narrowing context or giving exclusion conditions. Several of these phrases are broad enough to match ordinary conversations about media projects, which could cause unintended invocation.
The examples send user prompts and local file references to a remote CLI service without a clear privacy or data-transmission warning. In a creative workflow, prompts, script details, shot plans, and local filenames may contain proprietary or unreleased production information, so silent remote transmission materially increases confidentiality risk.
The skill includes software installation and remote service usage even though its stated purpose is instructional storyboard creation. In context, that makes the capability more dangerous because users invoking a planning skill may not expect shell installation, authentication, or data transmission to third-party services, creating elevated supply-chain and privacy risk.
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.
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.
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.
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.
No suspicious patterns detected.