gemini-image-gen Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

gemini-image-gen is an AI agent skill, created by IISweetHeartII (Deokhwan Kim) and published at openclaw/skills. ClawSecure audited gemini-image-gen across 7 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 45/100 (High Risk). The 8 findings concentrate in Data Exfiltration, Policy Violation and Unauthorized Tool Use, including Pattern detected: base64.b64encode and Potentially dangerous code pattern detected: base64.*decode. 2 were rated high or critical severity.

Is gemini-image-gen safe?

ClawSecure audited gemini-image-gen and assigned a security score of 45/100 (High Risk), identifying 8 findings across Data Exfiltration and Policy Violation. Review the findings below before installing.

What did ClawSecure find in gemini-image-gen?

ClawSecure identified 8 findings in gemini-image-gen, concentrated in Data Exfiltration, Policy Violation and Unauthorized Tool Use. 2 were rated high or critical severity. The most severe include Pattern detected: base64.b64encode and Potentially dangerous code pattern detected: base64.*decode.

How was gemini-image-gen audited?

ClawSecure ran gemini-image-gen through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 7 files from openclaw/skills.

What does a score of 45 mean?

ClawSecure assigned gemini-image-gen a security score of 45/100, placing it in the High Risk range. This is driven by 8 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 gemini-image-gen

ClawSecure detected 8 security findings in gemini-image-gen, spanning Data Exfiltration, Policy Violation, Unauthorized Tool Use and Social Engineering.

critical · Pattern detected: base64.b64encode. Data Exfiltration finding detected in scripts/gen.py:116.
high · Potentially dangerous code pattern detected: base64.*decode. Code Injection finding detected in gen.py.
medium · Pattern detected: import urllib.request. Data Exfiltration finding detected in scripts/gen.py:20.
medium · Skill code uses network libraries but doesn't declare network.... Unauthorized Tool Use finding.
medium · Skill performs actions not reflected in its description. Social Engineering finding detected in SKILL.md.
medium · Script iterates through environment variables in.... Data Exfiltration finding detected in /tmp/url-scans/c732d509326a7eb5/scripts/gen.py.
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 gemini-image-gen

Audit external network connections

gemini-image-gen sends data to external endpoints. Confirm each destination is expected and authorized, and remove any callback that exfiltrates data. ClawSecure monitors for known exfiltration and C2 endpoints.

Resolve policy violations

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

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

gitlab-cli-skillsScore 55/100 nginx-analyzeScore 60/100 nginx-analyzeScore 60/100 nginx-analyzeScore 60/100 nginx-analyzeScore 60/100

Scanned on February 16, 2026. gemini-image-gen 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