Skills/ClawHub/zm-visual-prompt-img2-workflow

zm-visual-prompt-img2-workflow@0.1.0

VERIFIED· install only

Publisher claims: "ZM IMG2 视觉提示词编排。用于把漫画页、PPT 主视觉、封面/配图等结构化视觉需求，编译为可执行的 happy/gpt-image-2 提示词，并检查参考图、主角图、风格、禁止项和 IMG2 生产证据。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher jerryxn · publishing for 143 daysInstalls 527Last detonated 25 h ago
$clawhub install zm-visual-prompt-img2-workflow
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionSKILL.md:73 · File type combined with upload action — agent may exfiltrate local data filesFor actual runs, `summary.json` also points to the underlying `zm-img2-generation-direct` run directory and output image.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:111 · File type combined with upload action — agent may exfiltrate local data files- `summary.json.input_images` contains only the cat and husky references;Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/compile_and_run.py:227 · Python subprocess execution detectedproc = subprocess.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, timeout=args.timeout_ms / 1000 + 45)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionSKILL.md:113 · File type combined with upload action — agent may exfiltrate local data files- underlying `result.json` has `provider: happy`, `model: gpt-image-2`, `mode: edit`, `input_images` populated.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/compile_and_run.py:253 · File type combined with upload action — agent may exfiltrate local data fileswrite_json(run_dir / "result.json", {"ok": True, "stage": "dry_run", "mode": "edit" if input_images else "generation", "input_images": input_images})Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈994 tok
1 file · 7 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.