agent-selfie Security Audit Report
agent-selfie is an AI agent skill, created by IISweetHeartII (Deokhwan Kim) and published at iisweetheartii/agent-selfie. ClawSecure audited agent-selfie across 8 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 60/100 (Medium Risk). The 8 findings concentrate in Data Exfiltration, Unauthorized Tool Use and Social Engineering, including Potentially dangerous code pattern detected: base64.*decode and Skill code uses network libraries but doesn't declare network.... 1 was rated high or critical severity.
Is agent-selfie safe?
ClawSecure audited agent-selfie and assigned a security score of 60/100 (Medium Risk), identifying 8 findings across Data Exfiltration and Unauthorized Tool Use. Review the findings below before installing.
What did ClawSecure find in agent-selfie?
ClawSecure identified 8 findings in agent-selfie, concentrated in Data Exfiltration, Unauthorized Tool Use and Social Engineering. 1 was rated high or critical severity. The most severe include Potentially dangerous code pattern detected: base64.*decode and Skill code uses network libraries but doesn't declare network....
How was agent-selfie audited?
ClawSecure ran agent-selfie through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 8 files from iisweetheartii/agent-selfie.
What does a score of 60 mean?
ClawSecure assigned agent-selfie a security score of 60/100, placing it in the Medium Risk range. This reflects 8 findings led by Data Exfiltration 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-selfie
ClawSecure detected 8 security findings in agent-selfie, spanning Data Exfiltration, Unauthorized Tool Use, Social Engineering and Policy Violation.
- high · Potentially dangerous code pattern detected: base64.*decode. Code Injection finding detected in
selfie.py. - medium · Skill code uses network libraries but doesn't declare network.... Unauthorized Tool Use finding detected in
/tmp/url-scans/d3a049916bfac072/SKILL.md. - medium · Script iterates through environment variables in.... Data Exfiltration finding detected in
/tmp/url-scans/d3a049916bfac072/scripts/selfie.py. - medium · Skill performs actions not reflected in its description. Social Engineering finding detected in
SKILL.md. - medium · Pattern detected: urllib.request.Request(. Data Exfiltration finding detected in
scripts/selfie.py:127. - medium · Pattern detected: urllib.request.urlopen(. Data Exfiltration finding detected in
scripts/selfie.py:134. - 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-selfie
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. agent-selfie is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.