Skip to content
skillsafebeta
← Report library
Purpose / Other

Imagegen Frontend Mobile Skill Security Audit

What the author says it does (original text)

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mo

Independent security check

Security risks found

Files checked
1
Risks found
1
Could it run dangerous commands?Looks for programs run straight after downloading, remote control of your computer, and hidden commands.No risks found
Could it expose your files or keys?Looks for uploads of files containing passwords or keys, and keys written directly in the code.No risks found
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.No risks found
Could it bypass safety checks?Looks for skipped website security checks, excessive file access, or actions that skip your approval.No risks found
Could it mislead the AI or hide text?Checks the skill instructions for requests to ignore you, influence the report, or hide text in invisible characters.No risks found
Could it change links or payment recipients without asking?Looks for forced referral or payment changes combined with instructions to hide the change.Risks found: 1
Medium risk

Automatic extra screens and regeneration can consume more paid usage than expected

Source references: 5
What we found

The Skill directs the agent to add screens and detail renders whenever it judges them useful and to keep regenerating weak results, without first confirming a quantity or spending limit with the user.

Why this matters

If the underlying image service charges per generation or has a quota, a vague “app concept” request could produce several images and retries, increasing cost, exhausting credits, or extending completion time.

This is active default behavior, not an example: the Skill sets image-generation eagerness to its maximum, directs the agent to add screens and detail renders when it judges them useful, and requires further regeneration of weak results. If the image service charges per generation or has a usage quota, these extras—without a stated quantity cap or budget confirmation—could raise costs or exhaust quota. The source identifies no provider or pricing, so it supports only a conditional risk, not a claim that charges occurred. A user can ask for hard limits on images, retries, and budget, with confirmation before exceeding them.

SKILL.md:98In the instructionsOpen original file
  `(1 = repeated screen templates, 10 = clearly differentiated screen rhythm)`- IMAGE_GENERATION_EAGERNESS: 10    `(1 = minimal screens, 10 = generate as many screens and detail views as needed)`- SPACING_GENEROSITY: 9
Show 4 other places
SKILL.md:137In the instructionsOpen original file
- If the user says "fintech", "health", or "productivity", increase trust, calmness, and structural clarity.- Do not be lazy with screen count.- If more screens would make the flow better, generate more screens.- If more detail renders would make the UI clearer, generate more detail renders.- Default toward richer art direction than standard AI mobile output.
SKILL.md:1262In the instructionsOpen original file
## 34. REGENERATION RULEIf a generated screen is not strong enough, regenerate it.
SKILL.md:1287In the instructionsOpen original file
Do not settle for the first mediocre render.Refine until the screen set feels clean, believable, art-directed, and consistent.
SKILL.md:1340In the instructionsOpen original file
9. lock an internal design bible for consistency10. generate the required screen images11. generate more screens if needed for a believable flow12. generate extra detail renders if needed13. keep the first screen especially clean

Inside this skill

8 instruction sections

The Skill’s stated operating scope is generating mobile-app screen images and multi-screen flows; it explicitly prohibits code and implementation work.

View source
SKILL.md:77In the instructionsOpen original file
IMPORTANT:This skill generates images only.Do not switch into coding mode.Do not describe code.Do not build SwiftUI, React Native, Flutter, or HTML.Generate mobile screen images and screen-flow images only.

It infers the app category, platform, and screen count, then attempts to preserve one design system and a logical journey across multiple screens.

View source
SKILL.md:1330In the instructionsOpen original file
When the user asks for a mobile app image concept:1. infer app category2. infer platform mode3. infer number of screens4. choose a strong visual direction5. choose an image art direction bias6. choose a texture / surface treatment7. choose tasteful decorative assets8. choose a clean palette logic9. lock an internal design bible for consistency10. generate the required screen images11. generate more screens if needed for a believable flow12. generate extra detail renders if needed13. keep the first screen especially clean

The complete supplied source contains only SKILL.md, with no install steps, scripts, commands, credential requests, network-upload instructions, or file-modification instructions. This observation is limited to the supplied material and does not establish the safety of the underlying image tool or runtime.

View source
SKILL.md:32In the instructionsOpen original file
- desktop dashboards- image-to-code- frontend implementation- code generation
SKILL.md:1433In the instructionsOpen original file
This skill should create strong mobile app image concepts and flow images only.It should not write code.It should not behave like a website skill.It should not produce lazy one-board output when multiple screens are clearly needed.
Start here · InstructionsSKILL.md
imagegen-frontend-mobile
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source. 30 more sections are available in the original file.
Files and check records1 files

Coverage and gaps

Content covered in each file

These are the source ranges included in this check, not a guarantee that every issue has been resolved.

  • SKILL.mdFull text included

This report is for the version above. We read the available code and instructions without running the skill or checking extra packages it installs. This is not a promise of safety: a different version or setup may behave differently.

  • SKILL.mdInstructions
Lines read
1,466
File checksum (to compare versions)
a17e963ed5b0c05aa586023ccdf657f20a335a90e54e9c9a81c18c1fdda6e25d