Real Skill packageSource verifiedClawHub registry

AgentTrust — Security Scanner for AI Skills

Scan AI agent skills for malware, prompt injection, data exfiltration, and 47 other security threats. JWS-signed ACT/HALT receipts. x402-native, no API keys, no accounts. MCP manifest scanning.

Identity and source

Publisher attributionpoteshniyregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 71% rule confidence
Package forminstruction only1 recorded files
Canonical sourceClawHub registryclawhub:poteshniy:agenttrust-scanner
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 · 9/17/2026.claude/skills/<skill-name>
1 structural issue
  • error: SKILL.md does not contain a complete YAML frontmatter envelope. 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 · 9/17/2026.agents/skills/<skill-name>
1 structural issue
  • error: SKILL.md does not contain a complete YAML frontmatter envelope. 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 · 9/17/2026skills/<skill-name>
1 structural issue
  • error: SKILL.md does not contain a complete YAML frontmatter envelope. 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 @poteshniy/agenttrust-scanner
clawhub inspect @poteshniy/agenttrust-scanner --version 1.4.1

Security evidence

SkillVetAI static result: medium 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
full text content
Files
1 / 1 inspected as text
Checked
9/17/2026, 5:03:13 PM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
mediumSKILL.md has no parseable YAML frontmatterSKILL.md:1 · confidence 100%missing frontmatter
1 inferred permission indicators
  • network access — automatically inferred
3 dependency and API indicators
  • api: agenttrust.uk
  • api: datatracker.ietf.org
  • api: raw.githubusercontent.com
External clawhub result: clean

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
9/17/2026, 9:58:10 AM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

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

Package content hashsha256:0ffb8843cf1cd8faa7c5223337896bd00f625775d7a7608f3e4f046ba5b2125b
Show up to 1 recorded paths
  • SKILL.md

Source changelog

AgentTrust Scanner 1.4.1 introduces stricter privacy and consent requirements for all submissions. - Enhanced privacy notice: Explicitly states that content is sent outside the local machine, including for free scans. - Consent required: The agent must get explicit approval from users before sending any data, and redact sensitive information by default. - Revised instructions: Clarify to always disclose outbound submissions, avoid uploading secrets, and prefer local summarization for sensitive material. - MCP server install command now uses a pinned package version (@1.0.1) and removes automatic approval flags (no -y). - Removed file: skill-card.md.