gkn-phantomAutomated authorized penetration testing skill with multi-layer detection, PoC/exploit generation, comprehensive vulnerability reporting, and scope safety co...
Install via ClawdBot CLI:
clawdbot install yuanguin37/gkn-phantomGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdSends data to undocumented external endpoint (potential exfiltration)
send → https://attacker.evil.testHardcoded API key or token pattern found in skill definition
AKIAIOSFODNN...Potentially destructive shell commands in tool definitions
eval(Usage Guide
Loading usage data… refresh in a few seconds.
Scored Oct 18, 2026
Accesses system directories or attempts privilege escalation
sudo mvCalls external URL not in known-safe list
https://cwe.mitre.org/data/definitions/530.htmlUses known external API (expected, informational)
cloud.google.comAI Analysis
The skill is a legitimate penetration-testing tool, but the rule-based scan surfaced several concerning patterns: a hardcoded AWS-style access key (AKIAIOSFODNN...), references to /etc/passwd, an external callback endpoint (https://attacker.evil.test), and use of eval()/sudo. These are likely test fixtures or documentation examples within a pentest skill (e.g., demonstrating credential-file access, OOB SSRF validation via interactsh/ceye, and exploit PoC generation), which is consistent with its stated purpose. However, the presence of a hardcoded credential pattern and an attacker-controlled callback URL warrants a security warning, even though no confirmed exfiltration of user data was found.
Audited Oct 18, 2026 · audit v1.0
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
GEO Audit — AI Search Visibility Checker for ChatGPT, Perplexity, Claude & Gemini. 29-point GEO readiness checklist: robots.txt AI crawler access, Index...
Senior SecOps engineer skill for application security, vulnerability management, compliance verification, and secure development practices. Runs SAST/DAST sc...