Agentshield Audit

PendingCK: Medium

by bartelmost

1.9K downloads0 starsv1.0.3636 versions

Description

Privacy-First security audit with 77 local tests (52 live + 25 static). Works with OpenClaw, Hermes Agent, n8n (auto-detected), LangChain, and any AI agent p...

Changelog

- Removed old changelog files and documentation (CHANGELOG_v1.0.31.md, CHANGELOG_v1.32.md, skill-card.md) for a leaner package. - Updated skill description for clarity and conciseness. - Added "check agent security" to trigger phrases. - No new features or functionality changes.

agent-securityagentsai-safetyapi-securityauditcertificatescode-scancompliancecryptographyed25519eu-ai-acthuman-in-the-loopidentityllm-securityprivacyprivacy-firstprompt-injectionrate-limitingsecret-scanningsecuritytoken-optimizertrustv6.0verification

Published Feb 20, 2026Updated Jun 18, 2026

Security Analysis

ClawHub:

Pending

Clawkeeper:

CK: Medium

Risk Score4.0 / 10

Multiple risk signals — review findings before installing. Score is the sum of weighted findings below.

Findings

30 files analyzed

medium|+2.0 pts

Contains executable handler files (js/ts/sh/py)

medium|+1.5 pts

Binary file detected: sandbox_config.yaml (application/yaml)

low|+0.5 pts

30 files (typical skill has 1-3)

ClawHub scanned: Jun 18, 2026

Rescanned every 6 hours by Clawkeeper

Deploy Securely

Free to scan. Pro to deploy.