clawdbot-skill-manus Security Audit Report
clawdbot-skill-manus is an AI agent skill, created by DisierTECH and published at disi3r/openclaw-skill-manus. ClawSecure audited clawdbot-skill-manus across 11 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 24 findings concentrate in Data Exfiltration, Unauthorized Tool Use and Policy Violation, including Environment variable access with network calls in... and Multi-file exfiltration chain detected: scripts/get_result.py,.... 8 were rated high or critical severity.
Is clawdbot-skill-manus safe?
ClawSecure audited clawdbot-skill-manus and assigned a security score of 0/100 (High Risk), identifying 24 findings across Data Exfiltration and Unauthorized Tool Use. Review the findings below before installing.
What did ClawSecure find in clawdbot-skill-manus?
ClawSecure identified 24 findings in clawdbot-skill-manus, concentrated in Data Exfiltration, Unauthorized Tool Use and Policy Violation. 8 were rated high or critical severity. The most severe include Environment variable access with network calls in... and Multi-file exfiltration chain detected: scripts/get_result.py,....
How was clawdbot-skill-manus audited?
ClawSecure ran clawdbot-skill-manus through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 11 files from disi3r/openclaw-skill-manus.
What does a score of 0 mean?
ClawSecure assigned clawdbot-skill-manus a security score of 0/100, placing it in the High Risk range. This is driven by 24 findings led by Data Exfiltration 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 clawdbot-skill-manus
ClawSecure detected 24 security findings in clawdbot-skill-manus, spanning Data Exfiltration, Unauthorized Tool Use, Policy Violation and Permissions Manifest.
- critical · Environment variable access with network calls in.... Data Exfiltration finding.
- critical · Multi-file exfiltration chain detected: scripts/get_result.py,.... Data Exfiltration finding.
- critical · Script accesses environment variables and makes network calls in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/check_status.py. - critical · Script accesses environment variables and makes network calls in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/create_project.py. - critical · Script accesses environment variables and makes network calls in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/get_result.py. - critical · Script accesses environment variables and makes network calls in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/run_task.py. - critical · Script accesses environment variables and makes network calls in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/upload_file.py. - critical · Script accesses environment variables and makes network calls in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/webhook_server.py. - medium · Skill code uses network libraries but doesn't declare network.... Unauthorized Tool Use finding detected in
/tmp/url-scans/33929672ee699726/SKILL.md. - medium · Script iterates through environment variables in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/check_status.py. - medium · Script iterates through environment variables in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/create_project.py. - medium · Script iterates through environment variables in.... Data Exfiltration finding detected in
/tmp/url-scans/33929672ee699726/scripts/get_result.py.
Showing the 12 highest-severity of 24 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for clawdbot-skill-manus
Audit external network connections
Resolve policy violations
Add a config.json permissions manifest
Related Security Research
ClawHavoc Explained: The Malware Family Targeting AI Agents→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on May 6, 2026. clawdbot-skill-manus is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.