Real Skill packageSource verifiedClawHub registry

GKN Phantom

Automated authorized penetration testing skill with multi-layer detection, PoC/exploit generation, comprehensive vulnerability reporting, and scope safety co...

Identity and source

Publisher attributionTiwing08-rootregistry owner unverified by skillvetai
Functional categorySoftware Developmentautomatically inferred · 61% rule confidence
Package forminstruction with code64 recorded files
Canonical sourceClawHub registryclawhub:yuanguin37:gkn-phantom
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codeissues found
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/18/2026.claude/skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 3, column 14: description: GKN-Phantom — production-grade automated penetration testing and s… ^ SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexissues found
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/18/2026.agents/skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 3, column 14: description: GKN-Phantom — production-grade automated penetration testing and s… ^ SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawissues found
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/18/2026skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 3, column 14: description: GKN-Phantom — production-grade automated penetration testing and s… ^ SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @yuanguin37/gkn-phantom
clawhub inspect @yuanguin37/gkn-phantom --version 0.1.0

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
partial text content
Files
40 / 64 inspected as text
Checked
9/18/2026, 4:41:00 AM
Scanner
0.1.3
Policy
1.0.3
3 automated findings
mediumSKILL.md YAML frontmatter is invalidSKILL.md:1 · confidence 100%Nested mappings are not allowed in compact mappings at line 3, column 14: description: GKN-Phantom — production-grade automated penetration testing and s… ^
highDynamic code or shell execution is presentscripts/waf_evasion.py:347 · confidence 78%eval(
highEncoded content is decoded and executedscripts/waf_evasion.py:8 · confidence 90%base64
2 High/Critical review queue entries
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
7 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • browser control — automatically inferred
  • external write action — automatically inferred
30 dependency and API indicators
  • api: 100.100.100.200
  • api: 127.0.0.1.nip.io
  • api: 169.254.169.254
  • api: api.shodan.io
  • api: crt.sh
  • api: evil.com
  • api: evil.example.com
  • api: github.com
  • api: gkn-ssrf-url.oob.fake
  • api: internal.example.test
  • api: json.schemastore.org
  • api: kubernetes.default.svc
  • api: management.azure.com
  • api: metadata.google.internal
  • api: nvd.nist.gov
  • api: oob.authorized.test
  • api: origin
  • api: ptskilltest.oob.example.com
  • api: s3.amazonaws.com
  • api: search.censys.io
  • api: staging.example.test
  • api: storage.cloud.google.com
  • api: storage.googleapis.com
  • api: t
  • api: target.com
  • api: target.test
  • api: target1.com
  • api: target2.com
  • api: web.archive.org
  • api: www.shodan.io
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/18/2026, 2:36:20 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:b1ad3a09e504254622a009a47205c896b40b60a7a4d9996fa6207fe703c35672
Show up to 30 recorded paths
  • .gitignore
  • assets/example_input.json
  • assets/example_report.json
  • assets/example_trace.json
  • assets/manifest.yml
  • README.md
  • references/advanced_payload_playbook.md
  • references/data_schemas.md
  • references/formal_algorithms.md
  • references/payload_playbook.md
  • references/safety_policy.md
  • references/script_contracts.md
  • references/tool_contracts.json
  • rules/critical.yaml
  • rules/high.yaml
  • rules/low.yaml
  • rules/medium.yaml
  • rules/mutation_strategies.yaml
  • rules/waf_signatures.yaml
  • scripts/adaptive_engine.py
  • scripts/advanced_injection.py
  • scripts/advanced_sqli.py
  • scripts/api_auditor.py
  • scripts/attack_path.py
  • scripts/browser_agent.py
  • scripts/cloud_security.py
  • scripts/cn_probes.py
  • scripts/confidence_scoring.py
  • scripts/cve_correlator.py
  • scripts/decision_engine.py

Source changelog

GKN-Phantom v5.3.0 — Quick Combat Impact Chain Completed - Quick Combat Mode impact chain now fully implemented: from nuclei/built-in quick probes, to content-aware severity escalation, deep-dive adapter exploitation, parameter probing for SQLi/SSTI, through auto PoC/exploit generation and bundled combat reports. - New: Deep-dive adapters for exposed content (Actuator, GraphQL, Swagger) and parameter discovery with error-based injection probing. - Retains all v5 features: interactive browser agent (Playwright), multi-format reports (HTML/PDF), YAML rule config with hot-reload, and comprehensive test suite. - Supports 38 vulnerability types, 25+ WAF fingerprints, and 20+ attack chain patterns. - Strict safety controls enforced: in-scope/authorized testing only; reproducibility gate guarantees findings are live and reproducible. - Usable by trigger phrases including "penetration test," "s…