agency-agents Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

agency-agents is an AI agent skill, created by msitarzewski and published at msitarzewski/agency-agents. ClawSecure audited agency-agents across 84 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 45/100 (Warning). The 7 findings concentrate in Code Injection, ReDoS and Malicious Code, including Attempts to access sensitive file: SOUL.md and Potentially dangerous code pattern detected: eval\(. 4 were rated high or critical severity.

Is agency-agents safe?

ClawSecure audited agency-agents and assigned a security score of 45/100 (Warning), identifying 7 findings across Code Injection and ReDoS. Review the findings below before installing.

What did ClawSecure find in agency-agents?

ClawSecure identified 7 findings in agency-agents, concentrated in Code Injection, ReDoS and Malicious Code. 4 were rated high or critical severity. The most severe include Attempts to access sensitive file: SOUL.md and Potentially dangerous code pattern detected: eval\(.

How was agency-agents audited?

ClawSecure ran agency-agents through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 84 files from msitarzewski/agency-agents.

What does a score of 45 mean?

ClawSecure assigned agency-agents a security score of 45/100, placing it in the Warning range. This is driven by 7 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 agency-agents

ClawSecure detected 7 security findings in agency-agents, spanning Code Injection, ReDoS, Malicious Code and Permissions Manifest.

high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in README.md.
high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in engineering-ai-data-remediation-engineer.md.
high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in engineering-cms-developer.md.
high · Potentially dangerous code pattern detected: eval\(. Code Injection finding detected in engineering-rag-pipeline-engineer.md.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
medium · ReDoS vulnerability: Nested quantifiers (potential…. ReDoS finding detected in engineering-ats-validator-architect.md:106.
medium · ReDoS vulnerability: Extremely large quantifier range…. ReDoS finding detected in engineering-ats-validator-architect.md:162.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for agency-agents

Eliminate dynamic code execution

agency-agents 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.

Fix ReDoS-prone patterns

agency-agents contains regular expressions vulnerable to catastrophic backtracking (ReDoS). Replace vulnerable patterns, bound input length, and prefer linear-time matching so a crafted input cannot hang the agent.

Audit external network connections

agency-agents connects to external endpoints. Verify every outbound connection goes to a trusted destination. Unauthorized callbacks are a primary indicator of ClawHavoc malware and data exfiltration. ClawSecure's proprietary engine monitors for known malicious endpoints including C2 infrastructure.

Related Security Research

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

Related AI Agent Security Audits

agent-creditScore 53/100 mission-controlScore 38/100 theagentservice/skillsScore 35/100 self-improving-agent-3Score 30/100 @openclaw/dashboardScore 45/100

Scanned on October 19, 2026. agency-agents 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