Agent-Reach Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

Agent-Reach is an AI agent skill, created by Panniantong and published at Panniantong/Agent-Reach. ClawSecure audited Agent-Reach across 59 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 75/100 (Medium Risk). The 3 findings concentrate in Code Injection and Permissions Manifest, including Potentially dangerous code pattern detected: curl.*\|.*sh and Potentially dangerous code pattern detected: system\(. 2 were rated high or critical severity.

Is Agent-Reach safe?

ClawSecure audited Agent-Reach and assigned a security score of 75/100 (Medium Risk), identifying 3 findings across Code Injection and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in Agent-Reach?

ClawSecure identified 3 findings in Agent-Reach, concentrated in Code Injection and Permissions Manifest. 2 were rated high or critical severity. The most severe include Potentially dangerous code pattern detected: curl.*\|.*sh and Potentially dangerous code pattern detected: system\(.

How was Agent-Reach audited?

ClawSecure ran Agent-Reach through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 59 files from Panniantong/Agent-Reach.

What does a score of 75 mean?

ClawSecure assigned Agent-Reach a security score of 75/100, placing it in the Medium Risk range. This reflects 3 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 Agent-Reach

ClawSecure detected 3 security findings in Agent-Reach, spanning Code Injection and Permissions Manifest.

high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in cli.py.
high · Potentially dangerous code pattern detected: system\(. Code Injection finding detected in cli.py.
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 Agent-Reach

Eliminate dynamic code execution

Agent-Reach 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 Security→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→How to Secure an MCP Server: The 2026 Guide→

Related AI Agent Security Audits

hermes-agentScore 85/100 Agent-ReachScore 85/100 agent-skillsScore 85/100 agent-creditScore 75/100 probe-05-memory-readScore 75/100

Scanned on July 25, 2026. Agent-Reach 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