Audits, preserves and recovers local Git state before cleanup: unpushed or wrong-branch commits, dirty worktrees, duplicate clones, stashes, dangling commits, squash-merge uncertainty. Use when the user fears lost work, wants to recover a commit, asks if a branch is actually merged, asks whether a branch, worktree or clone is safe to delete, or wants one clean main (误删分支 / 还有没有丢的东西). Not for GitHub PR operations.
- 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 · 33
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:361 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:565 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:757 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:684 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:763 · skillspector:AE1
- high
Anti-Refusal: Anti-Refusal Statement
references/merge_verification.md:78 · skillspector:AR2
- high
Tool Misuse: Tool Parameter Abuse
references/merge_verification.md:438 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
references/prevention_practices.md:637 · skillspector:TM1
- high
YARA Match: YARA rule 'agent_skill_destructive_autonomous_actions': Autonomous destructive filesystem, shell history, or
references/recovery_playbook.md:202 · skillspector:YR1
- high
Tool Misuse: Tool Parameter Abuse
references/recovery_playbook.md:377 · skillspector:TM1
- high
Data Exfiltration: Env Variable Harvesting
scripts/git_export_before_drop.sh:509 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
scripts/git_stash_tree_archive.py:37 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_git_export_before_drop.py:43 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
scripts/git_prepare_sparse_worktree.py:30 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_git_classify_refs.py:42 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_git_prepare_sparse_worktree.py:26 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_git_verify_closeout.py:31 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
scripts/git_prepare_worktree_retirement.py:33 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
scripts/git_verify_closeout.py:238 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_git_prepare_worktree_retirement.py:29 · skillspector:E2
- high
Output Handling: Unvalidated Output Injection
tests/test_git_export_before_drop.py:1057 · skillspector:OH1
- high
Output Handling: Unvalidated Output Injection
tests/test_git_export_before_drop.py:1073 · skillspector:OH1
- high
Output Handling: Unvalidated Output Injection
tests/test_git_export_before_drop.py:1094 · skillspector:OH1
- high
Output Handling: Unvalidated Output Injection
tests/test_git_export_before_drop.py:1113 · skillspector:OH1
- high
Data Exfiltration: Env Variable Harvesting
tests/test_git_find_all_checkouts.py:84 · skillspector:E2
- high
Anti-Refusal: Anti-Refusal Statement
tests/test_git_loss_audit.py:17 · skillspector:AR2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_git_loss_audit.py:45 · skillspector:E2
- high
Privilege Escalation: Credential Access
tests/test_git_prepare_worktree_retirement.py:104 · skillspector:PE3
- high
Privilege Escalation: Credential Access
tests/test_git_prepare_worktree_retirement.py:308 · skillspector:PE3
- high
Privilege Escalation: Credential Access
tests/test_git_prepare_worktree_retirement.py:310 · skillspector:PE3
- high
Privilege Escalation: Credential Access
tests/test_git_prepare_worktree_retirement.py:310 · skillspector:PE3
- high
Privilege Escalation: Credential Access
tests/test_git_prepare_worktree_retirement.py:316 · skillspector:PE3
- high
Privilege Escalation: Credential Access
tests/test_git_prepare_worktree_retirement.py:328 · skillspector:PE3
medium · 17
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Rogue Agent: Session Persistence
references/merge_verification.md:940 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
references/merge_verification.md:940 · skillspector:RA2
- medium
Dangerous Code Execution: subprocess module call
scripts/git_prepare_sparse_worktree.py:34 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/git_prepare_worktree_retirement.py:38 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/git_stash_tree_archive.py:43 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/git_stash_tree_archive.py:124 · skillspector:AST4
- medium
Tool Misuse: Unsafe Defaults
scripts/git_stash_tree_archive.py:165 · skillspector:TM3
- medium
Dangerous Code Execution: subprocess module call
scripts/git_verify_closeout.py:272 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_git_align_checkout.py:63 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_git_hosted_vs_cached.py:41 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_git_preserve_danglers.py:50 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_git_verify_branch_merged_options.py:60 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_git_align_checkout.py:74 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_git_classify_refs.py:27 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_git_verify_branch_merged.py:30 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_git_verify_branch_merged_options.py:29 · skillspector:AST4
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-168 added, 8 changed High riskgot riskier
- v12026-11-03 No issues
Files
Files
33 files, 792 KB in total. Names only; open them on GitHub.
- SKILL.md
- agents/openai.yaml
- evals/evals.json
- references/merge_verification.md
- references/prevention_practices.md
- references/recovery_playbook.md
- references/worktree-retirement-helper.md
- scripts/git_align_checkout.sh
- scripts/git_classify_refs.sh
- scripts/git_export_before_drop.sh
- scripts/git_find_all_checkouts.sh
- scripts/git_hosted_vs_cached.sh
- scripts/git_loss_audit.sh
- scripts/git_prepare_clone_retirement.sh
- scripts/git_prepare_sparse_worktree.py
- scripts/git_prepare_worktree_retirement.py
- scripts/git_preserve_danglers.sh
- scripts/git_stash_tree_archive.py
- scripts/git_verify_branch_merged.sh
- scripts/git_verify_closeout.py
- tests/test_git_align_checkout.py
- tests/test_git_classify_refs.py
- tests/test_git_export_before_drop.py
- tests/test_git_find_all_checkouts.py
- tests/test_git_hosted_vs_cached.py
- tests/test_git_loss_audit.py
- tests/test_git_prepare_clone_retirement.py
- tests/test_git_prepare_sparse_worktree.py
- tests/test_git_prepare_worktree_retirement.py
- tests/test_git_preserve_danglers.py
- tests/test_git_verify_branch_merged.py
- tests/test_git_verify_branch_merged_options.py
- tests/test_git_verify_closeout.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
github-opsdaymadeOperates GitHub via gh CLI and REST/GraphQL: PRs, issues, Actions, self-hosted Runner inventory/capacity, repos, collaborators, org… High riskEngineeringDesign1.5k
lark-cli-routerdaymadeRoutes any Feishu/Lark/Doubao operation, including recording lookup by date (按日期找会议录音), through the version-matched lark-cli domain guide… High riskEngineeringProductivity1.5k
openclaw-model-switchdaymadeSwitches or repairs an OpenClaw instance's model config: changes the default model, adds model definitions, and fixes 401 "Invalid token",… High riskEngineeringAI & agents1.5k
peer-messagedaymadeBridges Claude Code and Codex sessions when native tools can't reach the target. Use for 跨产品通信 / 脚本回帖 / 送达排查: cross-product messages,… High riskEngineeringSecurity1.5k