Skills/ClawHub/award-polish

award-polish@1.0.5

VERIFIED· install only

Publisher claims: "Polish a website, landing page, web app, portfolio, or other browser UI toward award-winning, Awwwards-level quality. Use when the user sets Awwwards websites or award-winning web design as the bar, asks to polish or redesign a landing page, or needs to finish a timed take-home, portfolio website, or hackathon web project. Two independent reviewers score each batch and compare it against the best version so far. An optional helper can split polish changes into reviewable commits. Not for prose, documents, or non-web work, and not for writing award-submission essays." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher ekko237 · publishing for 10 daysInstalls 188Last detonated 3 h ago
$clawhub install award-polish
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 12 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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

What changed since 1.0.4

vet-skills diff award-polish 1.0.4 1.0.5

In the sandbox, this version reached for nothing 1.0.4 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 87/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: ModuleNotFoundError: No module named 'tinycss2'
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: calibrate.py: error: the following arguments are required: --round, --anchor, --model
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: ModuleNotFoundError: No module named 'playwright'
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: ModuleNotFoundError: No module named 'PIL'
0.4sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: review_prompt.py: error: the following arguments are required: --config, --anchor-shots, --current, --round
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1: ModuleNotFoundError: No module named 'requests'
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 1: ModuleNotFoundError: No module named 'PIL'
0.6sprocess8 of 12 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.6sprocessscript backend runs setup only
0.6sprocessscript backend runs setup only
0.6sprocessno install scripts to re-run

Static findings

MEDIUM
Declares no shell access; the code runs commandsscripts/_proc.py:62 · Declares no shell access; the code runs commands (stated in its permissions list)return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST02
MEDIUM
Python subprocess execution detectedscripts/_proc.py:62 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈5,855 tok
1 file · 27 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.

award-polish@1.0.5 safety verdict: Verified (install only) — KillerSkills