Seede Design Agent Skills

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned Seede design-generation skill, but it uses an external CLI/service, an API token, and may upload user assets.

Before installing, verify the Seede CLI package source, configure a dedicated expiring SEEDE_API_TOKEN, only use the skill for intended design tasks, and upload only assets you are comfortable sharing with the Seede service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Installing the CLI gives software from an external package source local execution capability.

Why it was flagged

The skill relies on installing a global third-party CLI package; this is expected for the stated purpose but should be verified by the user.

Skill content
npm install -g seede-cli
Recommendation

Verify the Seede CLI package name, publisher, and version before installing, and prefer trusted or pinned installation sources when available.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

The agent can run design-generation commands directly, which may create remote designs or consume service quota if used unintentionally.

Why it was flagged

The skill is designed for automated CLI execution without interactive prompts; that is purpose-aligned for agents but means actions should be clearly user-directed.

Skill content
Use `create` to generate designs. **Always use `--no-interactive` for autonomous execution.**
Recommendation

Use the skill for explicit design requests and require user confirmation for unusual, repeated, or account-impacting operations.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

Anyone or any agent with the token may be able to use the linked Seede account within the token's permissions.

Why it was flagged

The skill requires a Seede API token and documents token creation, which is expected for authentication but grants account-level service access.

Skill content
Recommended for Agents: Use `SEEDE_API_TOKEN` environment variable. Generate one using `seede token create`
Recommendation

Use a dedicated, least-privilege, expiring token for the agent and do not allow token creation or listing unless you intentionally request it.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

Logos, product images, or reference files provided to the skill may be uploaded to an external service and may need to be publicly accessible for use in designs.

Why it was flagged

The skill can upload local user assets to the Seede service and use returned URLs, so user content may leave the local environment.

Skill content
Upload images to use as references or materials. `seede upload ./path/to/logo.png` ... _Returns an Asset URL_
Recommendation

Only upload assets you are comfortable sending to Seede, avoid sensitive or confidential files, and review Seede's access and retention policies.