Skills/ClawHub/mia-trust

mia-trust@1.0.0

VERIFIED· install only

Publisher claims: "MIA-Trust Pipeline - Memory-Intelligent Assistant 信任守门+记忆进化 pipeline" Observed in sandbox: reads credential files.

Registry ClawHubPublisher sii-yucheng2002 · publishing for 231 daysInstalls 744Last detonated 2 h ago
$clawhub install mia-trust
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 6 of 6 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 (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 84/100 (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: reads credential files.

Behavior trace

Honeypot run · 3 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.8sprocessexec /usr/local/bin/npm
0.8sprocessbundled script run in the sandbox with no arguments
1.0sprocessbundled script run in the sandbox with no arguments
1.2sprocessexited 1: 用法: ./run.mjs "你的问题"
1.2sprocessbundled script run in the sandbox with no arguments
1.5sprocessexited 1: list [limit] - 列出反馈
1.5sprocessbundled script run in the sandbox with no arguments
1.7sprocessexited 1: list [limit] - 列出记忆(含效率分数)
1.7sprocessbundled script run in the sandbox with no arguments
1.9sprocessexited 1: Node.js v22.23.5
1.9sprocessbundled script run in the sandbox with no arguments
2.1sprocessexited 1: Node.js v22.23.5
2.1sprocess6 of 6 bundled scripts run with no arguments
2.1sprocessscript backend runs setup only
2.1sprocessscript backend runs setup only
2.4sprocesssecond launch, clock +45 days, CI unset
3.1sfilesystemread ~/.npmrc
3.1sfilesystemread ~/.npm/_logs outside project
3.1sprocessexec /usr/local/bin/npm

Static findings

MEDIUM
File type combined with upload actionSKILL.md:94 · File type combined with upload action — agent may exfiltrate local data files├── package.json # npm 配置(若存在根目录旧 trust_experience.json,postinstall 会同步到 trust/)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

No other findings across 3,127 lines in 12 files.

Cost to the agent

Instructions loaded
≈545 tok
1 file · 12 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.