skill-vetting Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

skill-vetting is an AI agent skill, created by eddygk and published at openclaw/skills. ClawSecure audited skill-vetting 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 16 findings concentrate in Code Injection, Prompt Injection and Command Injection, including Pattern detected: eval( and Pattern detected: exec(. 13 were rated high or critical severity.

Is skill-vetting safe?

ClawSecure audited skill-vetting and assigned a security score of 0/100 (High Risk), identifying 16 findings across Code Injection and Prompt Injection. Review the findings below before installing.

What did ClawSecure find in skill-vetting?

ClawSecure identified 16 findings in skill-vetting, concentrated in Code Injection, Prompt Injection and Command Injection. 13 were rated high or critical severity. The most severe include Pattern detected: eval( and Pattern detected: exec(.

How was skill-vetting audited?

ClawSecure ran skill-vetting 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 skill-vetting a security score of 0/100, placing it in the High Risk range. This is driven by 16 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 skill-vetting

ClawSecure detected 16 security findings in skill-vetting, spanning Code Injection, Prompt Injection, Command Injection and Policy Violation.

critical · Pattern detected: eval(. Command Injection finding detected in scripts/scan.py:20.
critical · Pattern detected: exec(. Command Injection finding detected in scripts/scan.py:21.
high · Pattern detected: os.system(. Command Injection finding detected in scripts/scan.py:27.
high · Pattern detected: Ignore all previous instructions. Prompt Injection finding detected in references/patterns.md:108.
high · Pattern detected: You are now in admin mode. Prompt Injection finding detected in references/patterns.md:121.
high · Pattern 'Ignore all previous instructions...' detected in asset file. Prompt Injection finding detected in references/patterns.md:108.
high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in patterns.md.
high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in SKILL.md.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in SKILL.md.
high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in patterns.md.
high · Potentially dangerous code pattern detected: exec\(. Code Injection finding detected in patterns.md.
high · Potentially dangerous code pattern detected: system\(. Code Injection finding detected in patterns.md.

Showing the 12 highest-severity of 16 findings. The full interactive list appears below.

3-Layer Audit Protocol

Security Recommendations for skill-vetting

Eliminate dynamic code execution

skill-vetting 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.

Investigate prompt injection vectors

Prompt injection is one of the most critical threats to AI agents. Attackers can embed malicious instructions in content the agent processes, causing unintended actions. Review every point where skill-vetting processes external content and add input validation and output filtering.

Harden command execution

skill-vetting 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.

Related Security Research

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

Related AI Agent Security Audits

a4b01e81f20e9814Score 0/100 understand-anythingScore 0/100 62ac696296b54aadScore 0/100 62ac696296b54aadScore 0/100 understand-anythingScore 0/100

Scanned on February 7, 2026. skill-vetting 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