clawscan Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

clawscan is an AI agent skill, created by g0head and published at openclaw/skills. ClawSecure audited clawscan across 4 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 0/100 (High Risk). The 19 findings concentrate in Command Injection, Unauthorized Tool Use and Code Injection, including Pattern detected: eval( and Pattern detected: exec(. 15 were rated high or critical severity.

Is clawscan safe?

ClawSecure audited clawscan and assigned a security score of 0/100 (High Risk), identifying 19 findings across Command Injection and Unauthorized Tool Use. Review the findings below before installing.

What did ClawSecure find in clawscan?

ClawSecure identified 19 findings in clawscan, concentrated in Command Injection, Unauthorized Tool Use and Code Injection. 15 were rated high or critical severity. The most severe include Pattern detected: eval( and Pattern detected: exec(.

How was clawscan audited?

ClawSecure ran clawscan through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 4 files from openclaw/skills.

What does a score of 0 mean?

ClawSecure assigned clawscan a security score of 0/100, placing it in the High Risk range. This is driven by 19 findings led by Command 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 clawscan

ClawSecure detected 19 security findings in clawscan, spanning Command Injection, Unauthorized Tool Use, Code Injection and Tool Chaining Abuse.

critical · Pattern detected: eval(. Command Injection finding detected in scripts/skillguard.py:104.
critical · Pattern detected: exec(. Command Injection finding detected in scripts/skillguard.py:107.
critical · Pattern detected: exec(. Command Injection finding detected in scripts/skillguard.py:108.
critical · Pattern detected: compile(. Command Injection finding detected in scripts/skillguard.py:110.
critical · Pattern detected: exec(. Command Injection finding detected in scripts/skillguard.py:124.
critical · Dangerous combination of code execution and system commands in.... Command Injection finding detected in /tmp/url-scans/94e53a9a99a7f551/scripts/skillguard.py.
high · Pattern detected: os.system(. Command Injection finding detected in scripts/skillguard.py:119.
high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in SKILL.md:82.
high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in SKILL.md:169.
high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in SKILL.md:83.
high · Detects system manipulation, privilege escalation, and destructive file.... Unauthorized Tool Use finding detected in SKILL.md:83.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in SKILL.md.

Showing the 12 highest-severity of 19 findings. The full interactive list appears below.

3-Layer Audit Protocol

Security Recommendations for clawscan

Harden command execution

clawscan constructs or runs system commands. Validate that commands are built only from trusted inputs, never pass user-controlled strings directly to a shell, and restrict execution to an allow-list of expected commands.

Eliminate dynamic code execution

clawscan 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

Why Generic Scanners Fail at AI Agent Security→Understanding Our 3-Layer Audit Protocol→

Related AI Agent Security Audits

byterover-cliScore 0/100 explain-code-for-developerScore 0/100 explain-code-for-developerScore 0/100 explain-code-for-developerScore 0/100 explain-code-for-developerScore 0/100

Scanned on February 7, 2026. clawscan 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