Skills/ClawHub/sai-creator

sai-creator@1.0.0

VERIFIED· install only

Publisher claims: "SAI — frontend builder untuk pipeline intel OJS/PKP. Render candidate yang sudah PASS dari SENKU menjadi tiga deliverable. Pertama, halaman artikel HTML sema..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher nijam727 · publishing for 199 daysInstalls 661Last detonated 38 min ago
$clawhub install sai-creator
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
4 of 4 bundled scripts run with no arguments, with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 91/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: ModuleNotFoundError: No module named 'yaml'
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: ModuleNotFoundError: No module named 'yaml'
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: render_carousel.py: error: the following arguments are required: --brief, --candidate, --dimension
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: validate_output.py: error: the following arguments are required: --html, --candidate
0.3sprocess4 of 4 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionSKILL.md:105 · File type combined with upload action — agent may exfiltrate local data filesRender via `scripts/render_carousel.py <brief.json> <dimension> <output.svg>`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Prompt injectionreferences/article-template-spec.md:136 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- [ ] Link external punya `rel="noopener"` dan icon/text indicatorFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/carousel-spec.md:129 · Prompt injection — known jailbreak technique reference · informational: not an instruction file## Icon Mapping (untuk visual anchor slide 1 dan 3-5)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:3 · Prompt injection — known jailbreak technique reference…halaman artikel HTML semantic, responsive, SEO-ready dengan meta tags, OG tags, dan JSON-LD schema.org Article. Kedua, carousel 7-slide struktur fix (hook, konteks…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/carousel-spec.md:3 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileSpesifikasi tipografi, palette, dimensi, dan A11y untuk carousel 7-slide SAI.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/carousel-spec.md:116 · Prompt injection — known jailbreak technique reference · informational: not an instruction file2. **Title & desc**: setiap SVG punya `<title>` dan `<desc>` di root untuk konteks AT.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈2,308 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.