← Back to Scanner

karakeep Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower
Source:
SHA-256:

karakeep is an AI agent skill, created by jayphen and published at openclaw/skills. ClawSecure audited karakeep across 3 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 40/100 (High Risk). The 7 findings concentrate in Data Exfiltration, Policy Violation and Unauthorized Tool Use, including Script accesses environment variables and makes network calls in... and Environment variable access with network calls in.... 2 were rated high or critical severity.

Is karakeep safe?

ClawSecure audited karakeep and assigned a security score of 40/100 (High Risk), identifying 7 findings across Data Exfiltration and Policy Violation. Review the findings below before installing.

What did ClawSecure find in karakeep?

ClawSecure identified 7 findings in karakeep, concentrated in Data Exfiltration, Policy Violation and Unauthorized Tool Use. 2 were rated high or critical severity. The most severe include Script accesses environment variables and makes network calls in... and Environment variable access with network calls in....

How was karakeep audited?

ClawSecure ran karakeep through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 3 files from openclaw/skills.

What does a score of 40 mean?

ClawSecure assigned karakeep a security score of 40/100, placing it in the High Risk range. This is driven by 7 findings led by Data Exfiltration that should be addressed before use. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).

Audit Findings for karakeep

ClawSecure detected 7 security findings in karakeep, spanning Data Exfiltration, Policy Violation, Unauthorized Tool Use and Permissions Manifest.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for karakeep

Audit external network connections
karakeep sends data to external endpoints. Confirm each destination is expected and authorized, and remove any callback that exfiltrates data. ClawSecure monitors for known exfiltration and C2 endpoints.
Resolve policy violations
karakeep trips ClawSecure policy checks. Review each flagged pattern against your security policy and remediate or document an accepted exception before production use.
Add a config.json permissions manifest
A config.json file declares what an agent component can access: file system, network, shell execution and more. Without it, users have no visibility into what the component can do before installing. This is the single most impactful security improvement for any AI agent skill.

Related Security Research

ClawHavoc Explained: The Malware Family Targeting AI AgentsBeyond Static Scans: Why ClawSecure Verifies Agentic Intent

Related AI Agent Security Audits

gnoScore 45/100openclawScore 55/100anthropic-cookbookScore 55/100ui-ux-pro-max-skillScore 55/100claude-memScore 35/100

Scanned on February 7, 2026. karakeep is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.

Start Your Free Scan