← Back to Scanner

skill-scanner Security Audit Report

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

skill-scanner is an AI agent skill, created by cisco-ai-defense and published at cisco-ai-defense/skill-scanner. ClawSecure audited skill-scanner across 54 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 65/100 (Medium Risk). The 4 findings concentrate in Code Injection and Permissions Manifest, including Potentially dangerous code pattern detected: eval\( and Potentially dangerous code pattern detected: exec\(. 3 were rated high or critical severity.

Is skill-scanner safe?

ClawSecure audited skill-scanner and assigned a security score of 65/100 (Medium Risk), identifying 4 findings across Code Injection and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in skill-scanner?

ClawSecure identified 4 findings in skill-scanner, concentrated in Code Injection and Permissions Manifest. 3 were rated high or critical severity. The most severe include Potentially dangerous code pattern detected: eval\( and Potentially dangerous code pattern detected: exec\(.

How was skill-scanner audited?

ClawSecure ran skill-scanner through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 54 files from cisco-ai-defense/skill-scanner.

What does a score of 65 mean?

ClawSecure assigned skill-scanner a security score of 65/100, placing it in the Medium Risk range. This reflects 4 findings led by Code Injection that warrant review before production 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-scanner

ClawSecure detected 4 security findings in skill-scanner, spanning Code Injection and Permissions Manifest.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for skill-scanner

Eliminate dynamic code execution
skill-scanner 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.
Pin dependencies to exact versions
Unpinned dependencies allow supply-chain attacks where a compromised version is pulled in automatically. Use exact version numbers in package.json (for example 1.2.3 instead of ^1.2.3) to keep unauthorized code out of your dependency tree. ClawSecure checks every dependency against known CVE databases.

Related Security Research

Why Generic Scanners Fail at AI Agent SecurityBeyond Static Scans: Why ClawSecure Verifies Agentic IntentHow to Secure an MCP Server: The 2026 Guide

Related AI Agent Security Audits

aitorScore 61/100openclawScore 55/100Anthropic-Cybersecurity-SkillsScore 65/100GitNexusScore 75/100antigravity-awesome-skillsScore 75/100

Scanned on August 4, 2026. skill-scanner 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