Operates GitHub via gh CLI and REST/GraphQL: PRs, issues, Actions, self-hosted Runner inventory/capacity, repos, collaborators, org permissions, 2FA, with explicit target, authorization, and independent readback. Use when a write reports success but state didn't change, or choosing gh/REST/GraphQL/UI-only. Not for local Git recovery (use git-safety-net), maintainer PR review (use github-review-pr), or upstream contribution (use github-contributor).
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 17 findings, highest severity high.
- Highest severity
- high
- Findings
- 17
- 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: 17 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 (17)
high · 10
- high
Tool Misuse: Tool Parameter Abuse
references/branch_protection.md:187 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
references/branch_protection.md:187 · skillspector:TM1
- high
Privilege Escalation: Credential Access
references/ghcr_publishing.md:41 · skillspector:PE3
- high
Privilege Escalation: Credential Access
references/multi_account_repository_sync.md:44 · skillspector:PE3
- high
Tool Misuse: Tool Parameter Abuse
references/pr_operations.md:583 · skillspector:TM1
- high
Privilege Escalation: Credential Access
references/workflow_operations.md:295 · skillspector:PE3
- high
Prompt Injection: Instruction Override
references/workflow_operations.md:341 · skillspector:P1
- high
Privilege Escalation: Credential Access
references/workflow_operations.md:525 · skillspector:PE3
- high
System Prompt Leakage: Direct Prompt Extraction
scripts/checked_gh.py:162 · skillspector:P6
- high
Data Exfiltration: Env Variable Harvesting
scripts/checked_gh.py:358 · skillspector:E2
medium · 7
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Excessive Agency: Autonomous Decision Making
references/api_reference.md:161 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
references/branch_protection.md:39 · skillspector:EA2
- medium
Rogue Agent: Session Persistence
references/workflow_operations.md:705 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
references/workflow_operations.md:706 · skillspector:RA2
- medium
Data Exfiltration: External Transmission
references/workflow_operations.md:754 · skillspector:E1
- medium
Data Exfiltration: External Transmission
references/workflow_operations.md:755 · skillspector:E1
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-167 changed High riskgot riskier
- v12026-11-03 No issues
Files
Files
13 files, 207 KB in total. Names only; open them on GitHub.
- SKILL.md
- references/api_reference.md
- references/best_practices.md
- references/branch_protection.md
- references/ci-demand-and-notifications.md
- references/ghcr_publishing.md
- references/issue_operations.md
- references/multi_account_repository_sync.md
- references/organization_access_and_settings.md
- references/pr_operations.md
- references/repository_operations.md
- references/workflow_operations.md
- scripts/checked_gh.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
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
qa-expertdaymadeSets up QA testing processes: test strategies, Google Testing Standards test cases, P0-P4 bug tracking, quality metrics, progress reports,… High riskEngineeringSecurity1.5k