Skills/ClawHub/nextai-image-forge

nextai-image-forge@0.1.1

CAUTION· static only

Publisher claims: "Use when an agent invokes ImageForge to generate or edit raster images with NextAI Code, configure API key/model, diagnose setup, or check whether the image-..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher nextai · publishing for 128 daysInstalls 722Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-11 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
npx invocation of non-well-known packagescripts/image_forge.py:1006 · npx invocation of non-well-known package — may execute untrusted codeupgrade = "npx skills update image-forge"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Fake instruction boundary tagreferences/troubleshooting.md:62 · Fake instruction boundary tag · informational: not an instruction filepython3 "$IMAGE_FORGE_SCRIPT" edit --brief '<approved brief>' --image '<path>' --prompt '<instruction>'Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagreferences/openai-compatible-images.md:56 · Fake instruction boundary tag · informational: not an instruction filepython3 "$IMAGE_FORGE_SCRIPT" edit --brief '<approved brief>' --image '<path>' --prompt '<instruction>'Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagreferences/openai-compatible-images.md:37 · Fake instruction boundary tag · informational: not an instruction file"prompt": "<prompt>",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagreferences/installation.md:99 · Fake instruction boundary tag · informational: not an instruction filepython3 "$IMAGE_FORGE_SCRIPT" edit --brief '<approved brief>' --image '<path>' --prompt '<instruction>'Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagreferences/openai-compatible-images.md:27 · Fake instruction boundary tag · informational: not an instruction filepython3 "$IMAGE_FORGE_SCRIPT" generate --brief '<approved brief>' --prompt '<prompt>'Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/image_forge.py:951 · Python subprocess execution detectedreturn subprocess.check_output(["git"] + list(args), cwd=cwd, stderr=subprocess.STDOUT).decode("utf-8")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Fake instruction boundary tagreferences/installation.md:93 · Fake instruction boundary tag · informational: not an instruction filepython3 "$IMAGE_FORGE_SCRIPT" generate --brief '<approved brief>' --prompt '<prompt>'Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionSKILL.md:69 · File type combined with upload action — agent may exfiltrate local data files3. Project config at `.image-forge/config.json` for `defaultModel` and `outputDir`Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagescripts/test_image_forge.py:863 · npx invocation of non-well-known package — may execute untrusted codeself.assertIn("npx skills update image-forge", result["upgradeCommand"])Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:59 · npx invocation of non-well-known package — may execute untrusted code…ORGE_SCRIPT` resolver above instead of hard-coding a single install directory. `npx skills add` may install to a workspace `.agents/skills/image-forge` directory, while o…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,693 tok
1 file · 11 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim nextai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim nextaiPropose a patch to the maintainer