auto-model-router Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

auto-model-router is an AI agent skill, created by joyyyced and published at joyyyced/auto-model-router. ClawSecure audited auto-model-router across 19 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 35 findings concentrate in Data Exfiltration, Command Injection and Code Injection, including Environment variable harvesting (scripts/feedback.py,… and Multi-File Data Exfiltration Chain. 10 were rated high or critical severity.

Is auto-model-router safe?

ClawSecure audited auto-model-router and assigned a security score of 0/100 (High Risk), identifying 35 findings across Data Exfiltration and Command Injection. Review the findings below before installing.

What did ClawSecure find in auto-model-router?

ClawSecure identified 35 findings in auto-model-router, concentrated in Data Exfiltration, Command Injection and Code Injection. 10 were rated high or critical severity. The most severe include Environment variable harvesting (scripts/feedback.py,… and Multi-File Data Exfiltration Chain.

How was auto-model-router audited?

ClawSecure ran auto-model-router through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 19 files from joyyyced/auto-model-router.

What does a score of 0 mean?

ClawSecure assigned auto-model-router a security score of 0/100, placing it in the High Risk range. This is driven by 35 findings led by Data Exfiltration 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 auto-model-router

ClawSecure detected 35 security findings in auto-model-router, spanning Data Exfiltration, Command Injection, Code Injection and Resource Abuse.

critical · Environment variable harvesting (scripts/feedback.py,…. Data Exfiltration finding.
critical · Multi-File Data Exfiltration Chain. Data Exfiltration finding.
critical · OS Command Execution. Command Injection finding detected in scripts/call_model.py:27.
critical · OS Command Execution. Command Injection finding detected in scripts/setup.py:20.
critical · OS Command Execution. Command Injection finding detected in scripts/update_route.py:32.
high · Suspicious Pattern: while True:. Resource Abuse finding detected in scripts/setup.py:141.
high · Variable $resp (from network at line 40: `resp=$(curl -sf…. Command Injection finding detected in scripts/test_router.sh:52.
high · Potentially dangerous code pattern detected: system\(. Code Injection finding detected in call_model.py.
high · Potentially dangerous code pattern detected: system\(. Code Injection finding detected in setup.py.
high · Potentially dangerous code pattern detected: system\(. Code Injection finding detected in update_route.py.
medium · Undeclared Network Access. Unauthorized Tool Use finding detected in SKILL.md.
medium · Environment Variable Enumeration. Data Exfiltration finding detected in router/main.py.

Showing the 12 highest-severity of 35 findings. The full interactive list appears below.

3-Layer Audit Protocol

Security Recommendations for auto-model-router

Audit external network connections

auto-model-router sends data to external endpoints. Confirm each destination is expected and authorized, and remove any callback that exfiltrates data. ClawSecure monitors for known exfiltration and C2 endpoints.

Harden command execution

auto-model-router 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

auto-model-router 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.

Related Security Research

ClawHavoc Explained: The Malware Family Targeting AI Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→

Related AI Agent Security Audits

openclaw-master-skillsScore 0/100 6bc837afc1a86e89Score 0/100 6bc837afc1a86e89Score 0/100 a4b01e81f20e9814Score 0/100 understand-anythingScore 0/100

Scanned on June 23, 2026. auto-model-router 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