CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

26.6 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 2 flagged

Securityscore 76 · 2 findings

MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · .cursor/skills/transparent-bg/SKILL.md

MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.

Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted

excerpt.cursor/skills/transparent-bg/SKILL.md· markdown

62## Prompt scaffold for fallback matting flow

64**Do not ask for transparency in the prompt.** Ask for pure white:

66```

Occurrences

1 occurrence · at L64

How to fix

Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.

Delete blanket "don't ask / no need to confirm" directives from the skill.
If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.

Framework references

OWASPLLM01 ATLASAML.T0051

Trace & refs

ruleSS-SKILL-INJECT-DONT-ASK-01sha25668b030f55bcd484a…rubric 365aacaView on GitHub

MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · CHANGELOG.md

MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.

Why it matters

The exact value spotted

excerptCHANGELOG.md· markdown

133- **Four new skills (→ 12 total).** Long-tail gaps the asset-type skills don't cover. No MCP

… (102 chars elided on L133)

134- `svg-authoring` — engaged whenever `asset_generate_*` returns an `InlineSvgPlan`. Enforces

… (106 chars elided on L134)

135- `t2i-prompt-dialect` — engaged during prompt rewriting. Per-model rules for `gpt-image-1`,

… (106 chars elided on L135)

136- `asset-validation-debug` — engaged when `asset_validate` or a generator returns warnings.

… (106 chars elided on L136)

137- `brand-consistency` — engaged for multi-asset sets. Builds `BrandBundle` (palette, typogra

… (106 chars elided on L137)

Occurrences

1 occurrence · at L135

How to fix

Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.

Delete blanket "don't ask / no need to confirm" directives from the skill.
If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.

Framework references

OWASPLLM01 ATLASAML.T0051

Trace & refs

ruleSS-SKILL-INJECT-DONT-ASK-01sha256183eb789192b5159…rubric 365aacaView on GitHub

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

.cursor/skills/transparent-bg/SKILL.md · 1 file

.cursor/skills/transparent-bg/SKILL.md4.1 KB · Markdown

name: transparent-bg

description: Produce a truly RGBA-transparent asset from a brief. Handles the #1 pain (Gemini/Imagen rendering checkerboard pixels instead of real alpha). Routes to native-RGBA providers; falls back to BiRefNet / BRIA RMBG / LayerDiffuse / difference matting.

trigger_phrases: [transparent background, transparent png, rgba, alpha channel, no background, cutout, isolated]

Transparent background

The problem (see research 13 + 04)

Almost every modern T2I VAE is RGB-only. Asking Imagen 3/4 or Gemini 2.5/3 Flash Image for a "transparent logo" triggers one of two failures:

Flat background — DALL·E 3, Stable Diffusion families render a white/gray background that must be matted.
Checkerboard as RGB pixels — Gemini/Imagen literally render the gray-and-white 8×8 tile pattern (because Photoshop screenshots in their training data show transparency that way). This is the "weird boxes" users report. It cannot be fixed by prompting.

Fix hierarchy (apply first that fits)

1. Route to a native-RGBA provider

Provider	Mechanism
`gpt-image-1` / `gpt-image-1.5`	API param `background: "transparent"` + `output_format: "png"` or `"webp"`
Ideogram 3 Turbo	Dedicated `/ideogram-v3/generate-transparent` endpoint; set `rendering_speed: "TURBO"` for Turbo tier
Recraft V3	native SVG output (alpha is trivial); rasterize if raster needed
LayerDiffuse on SDXL / Flux	In-diffusion-loop transparency adapter; better edges than post-matte

2. Post-process matte (for everything else)

Matting model	License	Strength
BiRefNet	MIT	Default choice 2026; best soft-edge handling
BRIA RMBG-2.0	CC-BY-NC-4.0 (hosted API for commercial)	Best overall quality
U²-Net	Apache-2.0	Legacy fallback
rembg	wrapper around U²-Net / BiRefNet	Easy CLI integration
SAM 2	Apache-2.0	For complex/multi-object scenes; 2-stage (segment → matte)

3. Difference matting (for semi-transparency: glass, hair, smoke)

Generate the same subject on pure-white background.
Generate again with same seed on pure-black background.
alpha = (white_version - black_version + 255) / 2 in luminance.
Works for true semi-transparent objects where rembg/BiRefNet produce hard-cutout artifacts.

4. Vectorize-and-drop (for flat marks)

Generate raster at 1024² on white background.
BiRefNet matte → K-means quantize to N colors → vtracer or potrace.
SVG has alpha trivially. Rasterize at target sizes with @resvg/resvg-js for RGBA PNGs.

Validation (never ship without)

Tier-0 alpha validator (see packages/mcp-server/src/pipeline/validate.ts):

1. Check PNG/WebP header has alpha channel type (RGBA, not RGB).
2. Reject if no pixels have alpha < 255 (it's opaque).
3. Reject if >5% of pixels have alpha ∈ [0.05, 0.95] AND FFT signature shows gray-tile band frequency (Gemini fake checkerboard).
4. Alpha coverage: subject pixels (alpha > 0.5) should occupy 30–85% of frame (sanity check).
5. Premultiplied-alpha check: no RGB values where alpha==0 (cleanup artifacts).

Prompt scaffold for fallback matting flow

Do not ask for transparency in the prompt. Ask for pure white:

[SUBJECT, concrete].
Centered, isolated, no surrounding context or props.
Solid pure white #FFFFFF background.
Clean silhouette with distinct outline.
No drop shadow, no ground plane, no reflection.
1:1 square, 1024x1024.

Then post-process with BiRefNet / BRIA.

Never do this

"transparent background" as a prompt to Imagen or Gemini (checkerboard result).
Trust output_format: "png" alone to produce alpha (PNG supports alpha, but the model has to emit it).
Algorithmic #FFFFFF → alpha=0 thresholding (loses anti-aliasing, creates jagged edges).
Post-resize RGBA with non-premultiplied alpha (dark fringes).

Output

transparent/
├── mark.png         # RGBA, validated
├── [email protected]      # optional high-DPI
├── mark.svg         # if vector path chosen
└── meta.json        # alpha_coverage, matting_method, validation_hash

transparent-bg-a4e54e— agent skill

Is transparent-bg-a4e54e safe to install?

Transparent background

The problem (see research 13 + 04)

Fix hierarchy (apply first that fits)

1. Route to a native-RGBA provider

2. Post-process matte (for everything else)

3. Difference matting (for semi-transparency: glass, hair, smoke)

4. Vectorize-and-drop (for flat marks)

Validation (never ship without)

Prompt scaffold for fallback matting flow

Never do this

Output

Audit the pieces. Scan the whole. Decide.