← Back to Scanner

model-router Security Audit Report

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

model-router is an AI agent skill, created by digitaladaption and published at digitaladaption/model-router. ClawSecure audited model-router across 8 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 70/100 (Medium Risk). The 4 findings concentrate in Social Engineering, Policy Violation and Prompt Injection, including Detects coercive prompt injections in tool description fields: hidden... and Skill name or description contains 'Anthropic', suggesting official.... 1 was rated high or critical severity.

Is model-router safe?

ClawSecure audited model-router and assigned a security score of 70/100 (Medium Risk), identifying 4 findings across Social Engineering and Policy Violation. Review the findings below before installing.

What did ClawSecure find in model-router?

ClawSecure identified 4 findings in model-router, concentrated in Social Engineering, Policy Violation and Prompt Injection. 1 was rated high or critical severity. The most severe include Detects coercive prompt injections in tool description fields: hidden... and Skill name or description contains 'Anthropic', suggesting official....

How was model-router audited?

ClawSecure ran model-router through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 8 files from digitaladaption/model-router.

What does a score of 70 mean?

ClawSecure assigned model-router a security score of 70/100, placing it in the Medium Risk range. This reflects 4 findings led by Social Engineering 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 model-router

ClawSecure detected 4 security findings in model-router, spanning Social Engineering, Policy Violation, Prompt Injection and Permissions Manifest.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for model-router

Resolve policy violations
model-router trips ClawSecure policy checks. Review each flagged pattern against your security policy and remediate or document an accepted exception before production use.
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 model-router processes external content and add input validation and output filtering.
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

OWASP ASI Top 10 Explained: The Complete Guide to AI Agent Security Standards→Understanding Our 3-Layer Audit Protocol→The Sleeper Agent Problem: Why a Clean Scan Today Does Not Guarantee Safety Tomorrow→

Related AI Agent Security Audits

skill-scannerScore 65/100anthropic-cookbookScore 75/100crewAIScore 85/100zeroclawScore 85/100MiroFishScore 80/100

Scanned on May 6, 2026. 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