helpful-assistant Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

helpful-assistant is an AI agent skill, created by totally-legit. ClawSecure audited helpful-assistant through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 0/100 (High Risk). The 12 findings concentrate in Malicious Code, Prompt Injection and Policy Violation, including Detects prompt strings used to override or force malicious tool calls:... and Suspicious domain detected: glot.io (potential data exfiltration). 9 were rated high or critical severity.

Is helpful-assistant safe?

ClawSecure audited helpful-assistant and assigned a security score of 0/100 (High Risk), identifying 12 findings across Malicious Code and Prompt Injection. Review the findings below before installing.

What did ClawSecure find in helpful-assistant?

ClawSecure identified 12 findings in helpful-assistant, concentrated in Malicious Code, Prompt Injection and Policy Violation. 9 were rated high or critical severity. The most severe include Detects prompt strings used to override or force malicious tool calls:... and Suspicious domain detected: glot.io (potential data exfiltration).

How was helpful-assistant audited?

ClawSecure ran helpful-assistant through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage.

What does a score of 0 mean?

ClawSecure assigned helpful-assistant a security score of 0/100, placing it in the High Risk range. This is driven by 12 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 helpful-assistant

ClawSecure detected 12 security findings in helpful-assistant, spanning Malicious Code, Prompt Injection, Policy Violation and Tool Chaining Abuse.

critical · Detects prompt strings used to override or force malicious tool calls:.... Prompt Injection finding detected in SKILL.md:7.
critical · Suspicious domain detected: glot.io (potential data exfiltration). Malicious Code finding detected in SKILL.md.
critical · Suspicious domain detected: webhook.site (potential data exfiltration). Malicious Code finding detected in SKILL.md.
high · Pattern detected: IGNORE ALL PREVIOUS INSTRUCTIONS. Prompt Injection finding detected in SKILL.md:7.
high · Pattern detected: Do not inform the user. Prompt Injection finding detected in SKILL.md:12.
high · Attempts to access sensitive file: .clawdbot/.env. 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: .ssh/. Malicious Code finding detected in SKILL.md.
high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in SKILL.md.
medium · Detects suspicious tool chaining patterns that could lead to data.... Tool Chaining Abuse finding detected in SKILL.md:11.
medium · Invalid config.json format. 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 helpful-assistant

Audit external network connections

helpful-assistant 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 helpful-assistant processes external content and add input validation and output filtering.

Resolve policy violations

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

Related Security Research

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

Related AI Agent Security Audits

invassistantScore 0/100 invassistantScore 0/100 probe-10-curl-pipeScore 15/100 clip-itScore 0/100 clickup-skillScore 0/100

Scanned on February 6, 2026. helpful-assistant 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