Static lint for Claude Code plugins and skills, with experimental LLM scoring for skills
- Stars
- 42,753
- Version
- v3
- Copies
- 0
Overview
Waxell rates it high risk: 16 findings, highest severity high.
- Highest severity
- high
- Findings
- 16
- 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 plugin's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
High risk Waxell rates it high risk: 16 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 (16)
high · 1
- high
Anti-Refusal: Anti-Refusal Statement
tests/test_cli.py:59 · skillspector:AR2
medium · 15
- medium
Dangerous Code Execution: subprocess module call
tests/test_eval_all.py:9 · skillspector:AST4
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:43 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_static.py:64 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:43 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:81 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:101 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:152 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:170 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:201 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:218 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:237 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:253 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:270 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:185 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
tests/test_parser.py:220 · skillspector:AS3
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v3 (0.1.5)2026-11-195 changed High riskgot riskier
- v2 (0.1.4)2026-11-165 changed No issues
- v1 (0.1.3)2026-11-03 No issues
Files
Files
50 files, 425 KB in total. Names only; open them on GitHub.
- .claude-plugin/plugin.json
- .codex-plugin/plugin.json
- .python-version
- README.md
- agents/eval-judge.md
- agents/eval-orchestrator.md
- commands/certify.md
- commands/compare.md
- commands/eval.md
- pyproject.toml
- scripts/eval_all.py
- skills/evaluation-methodology/SKILL.md
- skills/evaluation-methodology/references/improving-scores.md
- skills/evaluation-methodology/references/rubrics.md
- src/plugin_eval/__init__.py
- src/plugin_eval/cli.py
- src/plugin_eval/corpus.py
- src/plugin_eval/elo.py
- src/plugin_eval/engine.py
- src/plugin_eval/layers/__init__.py
- src/plugin_eval/layers/_sdk.py
- src/plugin_eval/layers/harness_portability.py
- src/plugin_eval/layers/judge.py
- src/plugin_eval/layers/monte_carlo.py
- src/plugin_eval/layers/static.py
- src/plugin_eval/models.py
- src/plugin_eval/parser.py
- src/plugin_eval/py.typed
- src/plugin_eval/reporter.py
- src/plugin_eval/snapshot.py
- src/plugin_eval/stats.py
- tests/__init__.py
- tests/conftest.py
- tests/test_cli.py
- tests/test_corpus.py
- tests/test_e2e.py
- tests/test_elo.py
- tests/test_engine.py
- tests/test_eval_all.py
- tests/test_harness_portability.py
- tests/test_judge.py
- tests/test_models.py
- tests/test_monte_carlo.py
- tests/test_no_trace_harness.py
- tests/test_parser.py
- tests/test_reporter.py
- tests/test_snapshot.py
- tests/test_static.py
- tests/test_stats.py
- uv.lock
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
protect-mcpwshobsonCedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin, receipts… High riskEngineeringAI & agents43k
bluesky-feeddavila7Your Bluesky timeline in a side pane: the posts of the accounts you follow, a field to write and send a post, and a like button on every… High riskEngineeringDocuments34k
neon-branch-per-sessiondavila7A Neon database branch for each Claude Code session: created from your default (or chosen) branch when the session starts, handed to every… High riskEngineeringData & analytics34k
rex-ttydavila7Inside the Rex terminal, runs the Bash commands that need a real terminal (sudo, gh auth login, git rebase -i, a key passphrase) in a Rex… High riskEngineeringAI & agents34k