@martian-engineering/lossless-claw Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

@martian-engineering/lossless-claw is an AI agent skill, created by Josh Lehman <josh@martian.engineering> and published at Martian-Engineering/lossless-claw. ClawSecure audited @martian-engineering/lossless-claw across 53 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 15/100 (High Risk). The 8 findings concentrate in Code Injection, Permissions Manifest and Malicious Code, including Vulnerability in vitest@3.0.0: Vitest allows Remote Code Execution when... and Attempts to access sensitive file: .ssh/. 7 were rated high or critical severity.

Is @martian-engineering/lossless-claw safe?

ClawSecure audited @martian-engineering/lossless-claw and assigned a security score of 15/100 (High Risk), identifying 8 findings across Code Injection and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in @martian-engineering/lossless-claw?

ClawSecure identified 8 findings in @martian-engineering/lossless-claw, concentrated in Code Injection, Permissions Manifest and Malicious Code. 7 were rated high or critical severity. The most severe include Vulnerability in vitest@3.0.0: Vitest allows Remote Code Execution when... and Attempts to access sensitive file: .ssh/.

How was @martian-engineering/lossless-claw audited?

ClawSecure ran @martian-engineering/lossless-claw through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 53 files from Martian-Engineering/lossless-claw.

What does a score of 15 mean?

ClawSecure assigned @martian-engineering/lossless-claw a security score of 15/100, placing it in the High Risk range. This is driven by 8 findings led by Code Injection 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 @martian-engineering/lossless-claw

ClawSecure detected 8 security findings in @martian-engineering/lossless-claw, spanning Code Injection, Permissions Manifest, Malicious Code and Supply Chain.

critical · Vulnerability in vitest@3.0.0: Vitest allows Remote Code Execution when.... Supply Chain finding detected in package.json.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in lcm-blob-migrate.mjs.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in fts5.md.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in lcm-blob-migrate.mjs.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in stub-tier-assemble-bench.mjs.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in stub-tier-drilldown-harness.mjs.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in stub-tier-live-watcher.mjs.
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 @martian-engineering/lossless-claw

Eliminate dynamic code execution

@martian-engineering/lossless-claw 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.

Audit external network connections

@martian-engineering/lossless-claw 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.

Related Security Research

Why Generic Scanners Fail at AI Agent Security→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→

Related AI Agent Security Audits

6bc837afc1a86e89Score 0/100 @martian-engineering/lossless-clawScore 25/100 @martian-engineering/lossless-clawScore 25/100 understand-anythingScore 0/100 memory-lancedb-proScore 0/100

Scanned on May 31, 2026. @martian-engineering/lossless-claw 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