Isolates profiles for multi-provider setup and switching models in separate terminal windows (Kimi, MiniMax, DeepSeek, GLM, StepFun, Anthropic). Use for provider switching, csk/csd/csg aliases, CLAUDE_CONFIG_DIR, ~/.claude-profiles, profile drift (missing skills/hooks, symlinks, settings), context-window setup ([1m], CLAUDE_CODE_MAX_CONTEXT_TOKENS), or reducing startup context from preloaded MCP tool schemas.
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 50 findings, highest severity high.
- Highest severity
- high
- Findings
- 50
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked yesterday
Result
High risk Waxell rates it high risk: 50 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (50)
high · 50
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:36 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:49 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:224 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:231 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:372 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/local-source-sync-architecture.md:352 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/troubleshooting.md:122 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/troubleshooting.md:165 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/claude-plugins-sync.py:44 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/claude-profiles.sh:201 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/skill-install-audit.py:9 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:48 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:48 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:49 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:192 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:379 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:389 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:400 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:528 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:551 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/credential-storage.md:12 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/local-source-sync-architecture.md:448 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/student-setup-guide.md:67 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/student-setup-guide.md:151 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/troubleshooting.md:5 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/troubleshooting.md:8 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/troubleshooting.md:591 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/troubleshooting.md:608 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/claude-profiles.sh:6 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/setup.sh:97 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/setup.sh:98 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/sync-profile-settings.py:17 · skillspector:AS1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:152 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:368 · skillspector:AE1
- high
Data Exfiltration: Env Variable Harvesting
references/context-window-config.md:110 · skillspector:E2
- high
Privilege Escalation: Credential Access
references/credential-storage.md:13 · skillspector:PE3
- high
Excessive Agency: External Model or Provider Selection
references/mcp-startup-context.md:13 · skillspector:EA5
- high
Excessive Agency: External Model or Provider Selection
references/mcp-startup-context.md:122 · skillspector:EA5
- high
Agent Snooping: Agent Config Directory Access
references/mcp-startup-context.md:36 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/sync-local-skill-sources-daemon.sh:55 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/mcp-startup-context.md:40 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
scripts/setup.sh:10 · skillspector:AS1
- high
Excessive Agency: External Model or Provider Selection
references/mcp-startup-context.md:79 · skillspector:EA5
- high
Agent Snooping: MCP Config Access
references/mcp-startup-context.md:86 · skillspector:AS2
- high
Agent Snooping: Agent Config Directory Access
references/troubleshooting.md:42 · skillspector:AS1
- high
Anti-Refusal: Anti-Refusal Statement
references/troubleshooting.md:305 · skillspector:AR2
- high
Data Exfiltration: Env Variable Harvesting
scripts/claude-plugins-sync.test.py:54 · skillspector:E2
- high
Tool Misuse: Tool Parameter Abuse
scripts/sync-profile-settings.test.py:108 · skillspector:TM1
- high
Data Exfiltration: Env Variable Harvesting
tests/test_authoring_pools.py:158 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_credential_binding.py:44 · skillspector:E2
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-167 added, 9 changed, 2 removed High riskgot riskier
- v12026-11-03 No issues
Files
Files
47 files, 682 KB in total. Names only; open them on GitHub.
- SKILL.md
- assets/templates/anthropic.json
- assets/templates/codex-active-skills.json
- assets/templates/deepseek.json
- assets/templates/glm.json
- assets/templates/kimi-highspeed.json
- assets/templates/kimi.json
- assets/templates/legacy/minimax-m2-7-cn.json
- assets/templates/legacy/minimax-m2-7.json
- assets/templates/minimax-cn.json
- assets/templates/minimax-m3-cn.json
- assets/templates/minimax-m3.json
- assets/templates/minimax.json
- assets/templates/stepfun.json
- evals/trigger-evals.json
- references/context-window-config.md
- references/credential-storage.md
- references/headless-verification.md
- references/local-source-sync-architecture.md
- references/mcp-startup-context.md
- references/student-setup-guide.md
- references/troubleshooting.md
- scripts/claude-plugins-sync.py
- scripts/claude-plugins-sync.test.py
- scripts/claude-profiles.sh
- scripts/prune-source-sync-backups.py
- scripts/seed-codex-active-skills.py
- scripts/setup.sh
- scripts/skill-install-audit.py
- scripts/sync-daemon-recorder.sh
- scripts/sync-daemon-recorder.test.sh
- scripts/sync-local-skill-sources-daemon.sh
- scripts/sync-local-skill-sources.py
- scripts/sync-profile-settings.py
- scripts/sync-profile-settings.test.py
- tests/test_authoring_pools.py
- tests/test_credential_binding.py
- tests/test_daemon_interpreter_compat.py
- tests/test_daemon_runtime_lag.py
- tests/test_minimax_profiles.py
- tests/test_native_command.py
- tests/test_prune_source_sync_backups.py
- tests/test_setup.py
- tests/test_skill_install_audit.py
- tests/test_source_sync_daemon.py
- tests/test_sync_local_skill_sources.py
- tests/test_sync_state.py
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
prior-work-retrievaldaymadeOnly for explicit prior-work/reuse/history requests, not status checks. Finds and verifies existing work before new production when reuse… High riskEngineeringAI & agents1.5k
local-codexdaymadeLaunches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate… High riskEngineeringAI & agents1.5k
macos-cleanerdaymadeDiagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign… High riskEngineeringData & analytics1.5k
macos-watchdogdaymadeDesigns and audits macOS launchd watchdogs: LaunchAgent/LaunchDaemon setup, plist edits, scheduled self-healing, repeated notifications,… High riskEngineeringDesign1.5k