Skills/ClawHub/marktplaats

marktplaats@0.6.1

VERIFIED· install only

Publisher claims: "Marktplaats publisher 0.6.1: strictere gates en mini-model flow." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher roelbroersma · publishing for 129 daysInstalls 703Last detonated 3d ago
$clawhub install marktplaats
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 2026-11-11 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 · 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 actionbin/marktplaats-search.js:155 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(` Posted: ${listing.postedAt}`);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/marktplaats-place-probe.js:556 · File type combined with upload action — agent may exfiltrate local data filesif (result.upload?.hasFileInput != null) console.log(`upload file input: ${result.upload.hasFileInput ? 'yes' : 'no'}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Prompt injectionreferences/handleiding-nl.md:9 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…opassistent** Technische skill-key: `marktplaats`. Deze naam is bewust breder dan alleen zoeken. De skill helpt bij het volledige verkoopproces: categorie kiezen…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:131 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileVoor kleinere modellen geldt: één stap uitvoeren, output lezen, dan pas de volgende stap. Geen coördinatenkliks, geen verborgen submit en geen betaal-/promotieroute zonder expliciet akkoord.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:53 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileWil je twee minimale varianten afdwingen, herhaal dan `--variant` en gebruik `--min-variants 2`.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈444 tok
1 file · 16 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.