proactive-agent Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

proactive-agent is an AI agent skill, created by halthelobster and published at openclaw/skills. ClawSecure audited proactive-agent across 14 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 17 findings concentrate in Malicious Code, Prompt Injection and Permissions Manifest, including Pattern 'ignore previous instructions...' detected in asset… and Attempts to access sensitive file: SOUL.md. 15 were rated high or critical severity.

Is proactive-agent safe?

ClawSecure audited proactive-agent and assigned a security score of 0/100 (High Risk), identifying 17 findings across Malicious Code and Prompt Injection. Review the findings below before installing.

What did ClawSecure find in proactive-agent?

ClawSecure identified 17 findings in proactive-agent, concentrated in Malicious Code, Prompt Injection and Permissions Manifest. 15 were rated high or critical severity. The most severe include Pattern 'ignore previous instructions...' detected in asset… and Attempts to access sensitive file: SOUL.md.

How was proactive-agent audited?

ClawSecure ran proactive-agent through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 14 files from openclaw/skills.

What does a score of 0 mean?

ClawSecure assigned proactive-agent a security score of 0/100, placing it in the High Risk range. This is driven by 17 findings led by Malicious Code 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 proactive-agent

ClawSecure detected 17 security findings in proactive-agent, spanning Malicious Code, Prompt Injection, Permissions Manifest and Policy Violation.

high · Pattern 'ignore previous instructions...' detected in asset…. Prompt Injection finding detected in assets/HEARTBEAT.md:11.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in SKILL-v2.3-backup.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in SKILL-v2.3-backup.md.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in SKILL-v3-draft.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in SKILL-v3-draft.md.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in SKILL.md.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in AGENTS.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in AGENTS.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in HEARTBEAT.md.
high · Attempts to access sensitive file: MEMORY.md. Malicious Code finding detected in MEMORY.md.
high · Attempts to access sensitive file: SOUL.md. Malicious Code finding detected in ONBOARDING.md.

Showing the 12 highest-severity of 17 findings. The full interactive list appears below.

3-Layer Audit Protocol

Security Recommendations for proactive-agent

Audit external network connections

proactive-agent 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.

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 proactive-agent 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.

Related Security Research

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

Related AI Agent Security Audits

@martian-engineering/lossless-clawScore 15/100 @martian-engineering/lossless-clawScore 15/100 byterover-cliScore 0/100 explain-code-for-developerScore 0/100 explain-code-for-developerScore 0/100

Scanned on March 10, 2026. proactive-agent 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