Waxell

skill

github-ops High risk

daymadedaymade/claude-code-skillsupdated

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).
daymade's own description, from the skill's files.
Stars
1,534
Version
v2
Copies
0

Overview

blockHigh risk

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.

  1. v22026-11-167 changed High riskgot riskier
  2. 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

See all