Real Skill packageSource verifiedClawHub registry

Agentsafe Audit

AI-powered smart contract security audit with x402 payment.

Identity and source

Publisher attributionluckyregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 63% rule confidence
Package forminstruction with code79 recorded files
Canonical sourceClawHub registryclawhub:luka1968:agentsafe
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 Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 10/24/2026.claude/skills/agentsafe-audit

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

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 10/24/2026.agents/skills/agentsafe-audit

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

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 10/24/2026skills/agentsafe-audit

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 @luka1968/agentsafe
clawhub inspect @luka1968/agentsafe --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 / 79 inspected as text
Checked
10/24/2026, 4:00:41 PM
Scanner
0.1.3
Policy
1.0.3
4 automated findings
mediumPrompt-override language requires reviewsrc/agentsafe/llm/prompts.py:10 · confidence 62%ignore previous instructions
mediumPrompt-override language requires reviewtests/test_agents.py:68 · confidence 62%IGNORE ALL PREVIOUS INSTRUCTIONS
highPackage contains a path commonly used for secrets.env.example · confidence 88%.env.example
highPackage contains a path commonly used for secrets.env.example.cloud · confidence 88%.env.example.cloud
2 High/Critical review queue entries
STATIC_SENSITIVE_FILE_IN_PACKAGEpending
STATIC_SENSITIVE_FILE_IN_PACKAGEpending
Open human review queue →
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
16 dependency and API indicators
  • pypi: httpx >=0.27
  • pypi: pydantic >=2.7
  • pypi: pydantic-settings >=2.3
  • pypi: fastmcp >=2.3
  • pypi: markdown >=3.6
  • pypi: redis >=5.0
  • api: api.etherscan.io
  • api: api.etherscan.test
  • api: api.example.com
  • api: github.com
  • api: llm.test
  • api: mainnet.infura.io
  • api: tally.so
  • api: x402.org
  • api: x402.workfern.com
  • api: your-deployment-host
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
10/24/2026, 12:34:28 PM
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 hashsha256:4988d65bec3277d435f98bf5d81e60e88e94f87a585c91b9faf3943d90d85ec0
Show up to 30 recorded paths
  • .dockerignore
  • .env.example
  • .env.example.cloud
  • .github/workflows/audit.yml
  • .github/workflows/docker-audit.yml
  • .gitignore
  • agentsafe-deploy.zip
  • api/index.py
  • DEPLOYMENT.md
  • docker-compose.yml
  • Dockerfile
  • Dockerfile.server
  • fastmcp.json
  • favicon.ico
  • logo.png
  • mcphosting.json
  • openapi.json
  • PRIVACY_POLICY.md
  • pyproject.toml
  • railway.json
  • README.md
  • REFUND_POLICY.md
  • requirements.txt
  • scripts/run_audit.py
  • scripts/smoke_providers.py
  • skill-card.md
  • SKILL.md
  • src/agentsafe/__init__.py
  • src/agentsafe/__main__.py
  • src/agentsafe/agents/__init__.py

Source changelog

- Added the Agentsafe smart contract audit skill. - Supports paid audits for 3.00 USDC on Base and free contract information lookups. - Audits return a task ID for status polling.