Real Skill packageSource verifiedClawHub registry

token-safety-checker

Find and fix leaked API keys, tokens and passwords in your AI agent's config, long/short-term memory and session transcripts (OpenClaw + Claude Code). Use when the user asks to check token or secret safety, scan for leaked credentials, audit agent memory, MEMORY.md, CLAUDE.md or chat history for secrets, move plaintext tokens in openclaw.json to env vars, or stop secrets from being written into memory. Also use after editing openclaw.json or when setting up a new OpenClaw instance. Secret values are never printed.

Identity and source

Publisher attributionxinyuregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 67% rule confidence
Package forminstruction with code5 recorded files
Canonical sourceClawHub registryclawhub:maoisdamao:token-safety-checker
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 · 10/29/2026.claude/skills/token-safety-checker

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 · 10/29/2026.agents/skills/token-safety-checker

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 · 10/29/2026skills/token-safety-checker

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 @maoisdamao/token-safety-checker
clawhub inspect @maoisdamao/token-safety-checker --version 3.0.2

Security evidence

SkillVetAI static result: no findings detected

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
5 / 5 inspected as text
Checked
10/29/2026, 5:43:24 AM
Scanner
0.1.3
Policy
1.0.3
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
2 dependency and API indicators
  • api: clawhub.ai
  • api: github.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
10/29/2026, 4:40:55 AM
Release binding
Matches this record
  • vt: clean
  • 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:b1e96223c654ed9320875fa0270c49560d768a0521b419446e8623b533899a37
Show up to 5 recorded paths
  • LICENSE.md
  • README.md
  • scripts/safeclaw.py
  • skill-card.md
  • SKILL.md

Source changelog

Security hardening from the ClawHub review of 3.0.1 (ClawScan: "migration can leave passwords and tokens readable by other users"). ### Security - `migrate` no longer writes secret values into the shell profile. They go to a dedicated private secrets file (`~/.openclaw/tightlip.env`, or `tightlip.fish`), opened with mode 600 and fixed to 600 *before* any value is written; the profile only gets one line that loads it (`--no-profile` to skip, `--secrets-file` / `--profile` to choose paths). `--secure-profile` is obsolete - All rewrites (config, Claude settings, hook script, restore) go through exclusive private temp files (`mkstemp`) — no predictable names, no window with default permissions - Config and settings backups are created exclusively with mode 600 instead of copied then chmod-ed - `install-guard` requires an explicit `--platform claude|openclaw|all` (no auto-detection for persi…

Release security diff

mediumCompared fixed releases 3.0.1 and 3.0.2; 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
  • 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.

3.0.110/27/2026sha256:f37918acb8785069c0ed06bd861f22b7e4211c84be94bc532926ab9fc06724fe