← Back to Scanner

claw-control Security Audit Report

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

claw-control is an AI agent skill, created by adarshmishra07 and published at adarshmishra07/claw-control. ClawSecure audited claw-control across 75 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 25/100 (High Risk). The 10 findings concentrate in Code Injection, Skill Discovery Abuse and Policy Violation, including Attempts to access sensitive file: SOUL.md and Potentially dangerous code pattern detected: curl.*\|.*sh. 6 were rated high or critical severity.

Is claw-control safe?

ClawSecure audited claw-control and assigned a security score of 25/100 (High Risk), identifying 10 findings across Code Injection and Skill Discovery Abuse. Review the findings below before installing.

What did ClawSecure find in claw-control?

ClawSecure identified 10 findings in claw-control, concentrated in Code Injection, Skill Discovery Abuse and Policy Violation. 6 were rated high or critical severity. The most severe include Attempts to access sensitive file: SOUL.md and Potentially dangerous code pattern detected: curl.*\|.*sh.

How was claw-control audited?

ClawSecure ran claw-control through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 75 files from adarshmishra07/claw-control.

What does a score of 25 mean?

ClawSecure assigned claw-control a security score of 25/100, placing it in the High Risk range. This is driven by 10 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 claw-control

ClawSecure detected 10 security findings in claw-control, spanning Code Injection, Skill Discovery Abuse, Policy Violation and Permissions Manifest.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for claw-control

Eliminate dynamic code execution
claw-control 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.
Resolve policy violations
claw-control 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

Why Generic Scanners Fail at AI Agent SecurityBeyond Static Scans: Why ClawSecure Verifies Agentic Intent

Related AI Agent Security Audits

mission-controlScore 33/100@martian-engineering/lossless-clawScore 25/100@martian-engineering/lossless-clawScore 25/100openclaw-dashboard-repoScore 25/100openclaw-dashboard-repoScore 25/100

Scanned on February 23, 2026. claw-control 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