Real Skill packageSource verifiedClawHub registry

psyseal-scan

Offline, read-only scan of your AI agent (OpenClaw, Hermes Agent, nanobot, PicoClaw, ZeroClaw, NanoClaw or any agent folder): what loads on every message, what heartbeats and scheduled tasks cost, plaintext secrets, and planted or bloated memory. No network, no dependencies.

Identity and source

Publisher attributionPsysealregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 75% rule confidence
Package forminstruction with code33 recorded files
Canonical sourceClawHub registryclawhub:psyseal:psyseal-scan
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 · 11/10/2026.claude/skills/psyseal-scan

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 · 11/10/2026.agents/skills/psyseal-scan

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 · 11/10/2026skills/psyseal-scan

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 @psyseal/psyseal-scan
clawhub inspect @psyseal/psyseal-scan --version 0.3.3

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
full text content
Files
32 / 33 inspected as text
Checked
11/10/2026, 7:16:58 AM
Scanner
0.1.3
Policy
1.0.3
4 automated findings
highRemote content is piped directly to a shellsrc/scan.mjs:232 · confidence 98%curl … | sh
highEncoded content is decoded and executedsrc/detectors/injection.mjs:48 · confidence 90%base64
highEncoded content is decoded and executedsrc/detectors/secrets.mjs:67 · confidence 90%base64
highEncoded content is decoded and executedsrc/json5.mjs:154 · confidence 90%fromCharCode
4 High/Critical review queue entries
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_OBFUSCATED_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
5 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
  • api: platform.claude.com
  • api: polar.sh
  • api: psyseal.com
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
11/9/2026, 8:07:21 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:ec3ad502052dfc6bad4711c9916d1f0d7b1c64a14289553afe21669525dc76ec
Show up to 30 recorded paths
  • LICENSE-MIT0
  • package.json
  • README.md
  • scripts/psyseal-scan.mjs
  • skill-card.md
  • SKILL.md
  • src/brand.mjs
  • src/config.mjs
  • src/cost.mjs
  • src/detectors/bootstrap.mjs
  • src/detectors/injection.mjs
  • src/detectors/memory.mjs
  • src/detectors/secrets.mjs
  • src/fixable.mjs
  • src/i18n.mjs
  • src/json5.mjs
  • src/mcp.mjs
  • src/platforms/common.mjs
  • src/platforms/formats.mjs
  • src/platforms/generic.mjs
  • src/platforms/hermes.mjs
  • src/platforms/index.mjs
  • src/platforms/nanobot.mjs
  • src/platforms/nanoclaw.mjs
  • src/platforms/picoclaw.mjs
  • src/platforms/zeroclaw.mjs
  • src/pricing.mjs
  • src/report.mjs
  • src/safe.mjs
  • src/scan.mjs

Source changelog

MCP server mode (npx -y psyseal-scan mcp). Agent folders found with --path now show as "Agent folder" in English. Also on npm: npx psyseal-scan

Release security diff

mediumCompared fixed releases 0.1.0 and 0.3.3; 0 finding and 0 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Change reasons and limitations
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

0.1.011/6/2026sha256:a2e6890c98e287ad9411dffeb6f1c64fa0a1503e5f9d5f2a9894ce742c577782