heimdall is an AI agent skill, created by henrino3 and published at henrino3/heimdall. ClawSecure audited heimdall across 7 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 23 findings concentrate in Code Injection, Data Exfiltration and Malicious Code, including Dangerous combination of code execution and system commands in... and Pattern detected: exec(. 15 were rated high or critical severity.
Is heimdall safe?
ClawSecure audited heimdall and assigned a security score of 0/100 (High Risk), identifying 23 findings across Code Injection and Data Exfiltration. Review the findings below before installing.
What did ClawSecure find in heimdall?
ClawSecure identified 23 findings in heimdall, concentrated in Code Injection, Data Exfiltration and Malicious Code. 15 were rated high or critical severity. The most severe include Dangerous combination of code execution and system commands in... and Pattern detected: exec(.
How was heimdall audited?
ClawSecure ran heimdall through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 7 files from henrino3/heimdall.
What does a score of 0 mean?
ClawSecure assigned heimdall a security score of 0/100, placing it in the High Risk range. This is driven by 23 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 heimdall
ClawSecure detected 23 security findings in heimdall, spanning Code Injection, Data Exfiltration, Malicious Code and Command Injection.
- critical · Dangerous combination of code execution and system commands in.... Command Injection finding detected in
/tmp/url-scans/424bc59fb8c9c69e/scripts/skill-scan.py. - critical · Pattern detected: exec(. Command Injection finding detected in
scripts/test-skill-scan.py:55. - critical · Pattern detected: requests.post("https://webhook. Data Exfiltration finding detected in
scripts/test-skill-scan.py:56. - critical · Suspicious domain detected: webhook.site (potential data exfiltration). Malicious Code finding detected in
README.md. - critical · Suspicious domain detected: webhook.site (potential data exfiltration). Malicious Code finding detected in
SKILL.md. - critical · Suspicious domain detected: webhook.site (potential data exfiltration). Malicious Code finding detected in
test-skill-scan.py. - high · Pattern detected: ignore previous instructions. Prompt Injection finding detected in
SKILL.md:68. - high · Pattern detected: subprocess.run("id", shell=True. Command Injection finding detected in
scripts/test-skill-scan.py:53. - high · Attempts to access sensitive file: .ssh/. Malicious Code finding detected in
skill-scan.py. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
SKILL.md. - high · Potentially dangerous code pattern detected: curl.*\|.*sh. Code Injection finding detected in
skill-scan.py. - high · Potentially dangerous code pattern detected: base64.*decode. Code Injection finding detected in
skill-scan.py.
Showing the 12 highest-severity of 23 findings. The full interactive list appears below.
3-Layer Audit Protocol
Security Recommendations for heimdall
Eliminate dynamic code execution
Audit external network connections
Harden command execution
Related Security Research
Why Generic Scanners Fail at AI Agent Security→Beyond Static Scans: Why ClawSecure Verifies Agentic Intent→Related AI Agent Security Audits
Scanned on May 26, 2026. heimdall is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.