agent-council Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

agent-council is an AI agent skill, created by itsahedge and published at openclaw/skills. ClawSecure audited agent-council across 6 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 50/100 (Medium Risk). The 8 findings concentrate in Malicious Code, Data Exfiltration and Policy Violation, including Attempts to access sensitive file: SOUL.md and Attempts to access sensitive file: SOUL.md. 3 were rated high or critical severity.

Is agent-council safe?

ClawSecure audited agent-council and assigned a security score of 50/100 (Medium Risk), identifying 8 findings across Malicious Code and Data Exfiltration. Review the findings below before installing.

What did ClawSecure find in agent-council?

ClawSecure identified 8 findings in agent-council, concentrated in Malicious Code, Data Exfiltration and Policy Violation. 3 were rated high or critical severity. The most severe include Attempts to access sensitive file: SOUL.md and Attempts to access sensitive file: SOUL.md.

How was agent-council audited?

ClawSecure ran agent-council through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 6 files from openclaw/skills.

What does a score of 50 mean?

ClawSecure assigned agent-council a security score of 50/100, placing it in the Medium Risk range. This reflects 8 findings led by Malicious Code 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-council

ClawSecure detected 8 security findings in agent-council, spanning Malicious Code, Data Exfiltration, Policy Violation and Unauthorized Tool Use.

high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in README.md.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in create-agent.sh.
medium · Pattern detected: from urllib.request import. Data Exfiltration finding detected in scripts/rename_channel.py:21.
medium · Pattern detected: from urllib.request import. Data Exfiltration finding detected in scripts/setup_channel.py:21.
medium · Skill code uses network libraries but doesn't declare network.... Unauthorized Tool Use finding.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
info · Skill manifest does not include a 'license' field. Specifying a license.... Policy Violation finding detected in SKILL.md.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for agent-council

Audit external network connections

agent-council 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.

Resolve policy violations

agent-council trips ClawSecure policy checks. Review each flagged pattern against your security policy and remediate or document an accepted exception before production use.

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.

Related Security Research

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

Related AI Agent Security Audits

agency-agentsScore 55/100 mission-controlScore 38/100 theagentservice/skillsScore 35/100 ticktickScore 65/100 @openclaw/dashboardScore 45/100

Scanned on February 7, 2026. agent-council 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