keep Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

keep is an AI agent skill, created by hughpyle and published at hughpyle/keep. ClawSecure audited keep across 77 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 45/100 (High Risk). The 6 findings concentrate in Malicious Code, Code Injection and Permissions Manifest, including Attempts to access sensitive file: MEMORY.md and Attempts to access sensitive file: MEMORY.md. 5 were rated high or critical severity.

Is keep safe?

ClawSecure audited keep and assigned a security score of 45/100 (High Risk), identifying 6 findings across Malicious Code and Code Injection. Review the findings below before installing.

What did ClawSecure find in keep?

ClawSecure identified 6 findings in keep, concentrated in Malicious Code, Code Injection and Permissions Manifest. 5 were rated high or critical severity. The most severe include Attempts to access sensitive file: MEMORY.md and Attempts to access sensitive file: MEMORY.md.

How was keep audited?

ClawSecure ran keep through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 77 files from hughpyle/keep.

What does a score of 45 mean?

ClawSecure assigned keep a security score of 45/100, placing it in the High Risk range. This is driven by 6 findings led by Malicious Code 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 keep

ClawSecure detected 6 security findings in keep, spanning Malicious Code, Code Injection and Permissions Manifest.

high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in FLOW_STATE_DOCS.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in KEEP-FIND.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in OPENCLAW-INTEGRATION.md.
high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in README.md.
high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in HERMES-INTEGRATION.md.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for keep

Audit external network connections

keep connects to external endpoints. Verify every outbound connection goes to a trusted destination. Unauthorized callbacks are a primary indicator of ClawHavoc malware and data exfiltration. ClawSecure's proprietary engine monitors for known malicious endpoints including C2 infrastructure.

Eliminate dynamic code execution

keep evaluates code at runtime (for example eval or dynamic exec). Remove dynamic evaluation of untrusted input, and where code generation is unavoidable, sandbox it and validate every input.

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 Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→

Related AI Agent Security Audits

2fccdde2f962fa7cScore 55/100 7caf5d769dee89c3Score 55/100 7caf5d769dee89c3Score 55/100 2fccdde2f962fa7cScore 55/100 mission-controlScore 33/100

Scanned on July 17, 2026. keep 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