Skill Trust Decision
dlazy-text-storyboard-script
This is a legitimate storyboard-script generation skill that wraps a third-party dLazy CLI for optional image/video generation; all significant capabilities (shell:WRITE, network:READ to api.dlazy.com/files.dlazy.com, API key storage in ~/.dlazy/config.json) are declared in SKILL.md and metadata, though the main SKILL.md contains an internal contradiction between its 'no image generation' disclaimer and its execution instructions that command CLI invocation.
Why this conclusion was reached
0/4 dimensions flagged Pass
Declared vs actual capability
Declared resources and inferred behavior are broadly aligned.
Review
Hidden execution and egress
5 lower-risk artifacts were extracted and still need context.
Pass
Attack chain and severe findings
There is no explicit malicious chain in the report.
Pass
Dependencies and supply chain hygiene
Dependencies are present but no obvious high-risk issue stands out.
What drove the risk score up
Doc internal contradiction +10
SKILL.md 'Goals and Principles' says 'do not actually invoke tools to generate image/video/audio assets' but the 'CRITICAL EXECUTION INSTRUCTIONS' section explicitly commands running 'dlazy seedream-4.5 --prompt ...' CLI commands.
Version pin mismatch between files +5
SKILL.md metadata.clawdbot.install specifies '1.0.9' but the documentation body references '1.2.3' for npx and npm install commands.
API key stored on filesystem +5
Skill instructs saving the dLazy API key to ~/.dlazy/config.json; credential storage on disk is declared but worth monitoring.
Most important evidence
Medium Doc Mismatch
Internal documentation contradiction
SKILL.md 'Goals and Principles' section explicitly states 'This skill is only responsible for script generation; do not actually invoke tools to generate image/video/audio assets.' However, the 'CRITICAL EXECUTION INSTRUCTIONS' section at the bottom instructs the agent to execute terminal commands via the dLazy CLI (e.g., 'dlazy seedream-4.5 --prompt "..."'). This creates user confusion about the skill's actual scope.
SKILL.md:1 Remove the conflicting disclaimer or rephrase it to accurately reflect that the skill can optionally invoke the dLazy CLI for image generation with user confirmation.
Low Supply Chain
Version pin mismatch in metadata vs. documentation
The SKILL.md frontmatter metadata specifies install version '1.0.9' for the npm package, but the documentation body references '1.2.3' for npx invocations. Version inconsistencies could lead to unexpected behavior or confusion during installation.
SKILL.md:7 Ensure all version references are consistent across the SKILL.md metadata and documentation body.
Low Credential Theft
API key storage in user config directory
The skill instructs to save the dLazy API key to ~/.dlazy/config.json. While this is standard CLI behavior, the skill does not verify the file permissions are appropriately restricted after writing. A misconfigured CLI could leave the credential world-readable.
SKILL.md:14 Document that users should verify their OS-level file permissions on ~/.dlazy/config.json restrict access to the current user only (mode 600).
Declared capability vs actual capability
Shell Pass
Declared WRITE
→ Inferred WRITE
SKILL.md:21 — 'npm install -g @dlazy/[email protected]'; SKILL.md:47 — 'dlazy seedream-4.5 --prompt ...' Network Pass
Declared READ
→ Inferred READ
SKILL.md metadata: 'apiEndpoints: ["api.dlazy.com", "files.dlazy.com"]' Filesystem Pass
Declared WRITE
→ Inferred WRITE
SKILL.md:14 — stores API key to '~/.dlazy/config.json' Suspicious artifacts and egress
Medium External URL
https://www.npmjs.com/package/@dlazy/cli SKILL-cn.md:7
Medium External URL
https://dlazy.com SKILL-cn.md:32
Medium External URL
https://dlazy.com/dashboard/organization/api-key SKILL-cn.md:33
Medium External URL
https://clawhub.ai/user/dlazyai skill-card.md:9
Medium External URL
https://clawhub.ai/dlazyai/skills/dlazy-text-storyboard-script skill-card.md:35
Dependencies and supply chain
| Package | Version | Source | Known vuln | Notes |
|---|---|---|---|---|
| @dlazy/cli | 1.0.9 (metadata) / 1.2.3 (docs) | npm | No | Version mismatch between metadata install field and documentation body. Package not reviewed in this analysis — source at github.com/dlazy-ai/cli was not imported. |
File composition
4 files · 454 lines
Markdown 3 files · 449 linesJSON 1 files · 5 lines
Files of concern · 3
SKILL-cn.md https://www.npmjs.com/package/@dlazy/cli · https://dlazy.com · https://dlazy.com/dashboard/organization/api-key
SKILL.md Internal documentation contradiction · Version pin mismatch in metadata vs. documentation · API key storage in user config directory
skill-card.md https://clawhub.ai/user/dlazyai · https://clawhub.ai/dlazyai/skills/dlazy-text-storyboard-script
Other files · _meta.json
Security positives
All shell execution is explicitly declared in SKILL.md via npm install, npx, and dlazy CLI commands
Network access is explicitly declared via metadata.apiEndpoints: api.dlazy.com and files.dlazy.com
skill-card.md contains proactive risk disclosures about CLI usage and data sharing
No obfuscation, base64-encoded payloads, or hidden functionality observed
No credential harvesting beyond the skill's own API key (which is the user's own key)
No direct IP connections, reverse shells, or C2 communications detected
Source code repository (github.com/dlazy-ai/cli) is linked for review
Skill metadata includes alternative run method (npx) avoiding global installation