Skills/ClawHub/agenttrust-scanner

agenttrust-scanner@1.4.1

VERIFIED

Publisher claims: "Scan AI agent skills for malware, prompt injection, data exfiltration, and 47 other security threats. JWS-signed ACT/HALT receipts. x402-native, no API keys, no accounts. MCP manifest scanning." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher poteshniy · joined 0 days agoInstalls 1,889Last detonated 2 h ago
$clawhub install agenttrust-scanner
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 91/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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
npx invocation of non-well-known packageSKILL.md:99 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:13 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,470 tok
1 file · 2 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.

agenttrust-scanner@1.4.1 safety verdict: Verified 91/100 — KillerSkills