Waxell

plugin

security-guidance Review findings

Anthropicanthropics/claude-plugins-officialupdated

Browse GitHub Download zipBook a demo
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
Anthropic's own description, from the plugin's files.
SecurityAI & agentsEngineeringplugin
Stars
45,953
Version
v1
Copies
0
OverviewSecurity4Versions1Files61

Overview

holdReview findings

Waxell's checks found 4 findings to review, highest severity high.

Highest severity
high
Findings
4
What ran
Static analysis

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

Review findings Waxell's checks found 4 findings to review, highest severity high.

Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work

Findings (4)

high · 4

  • high

    Tells Claude to install unpinned packages (raised/timed, out)

    hooks/ensure_agent_sdk.py:58 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (is, also, memory-heavy, so, it, too …)

    hooks/ensure_agent_sdk.py:480 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (can, take)

    hooks/ensure_agent_sdk.py:885 · skill_risk:S2

  • high

    Tells Claude to install unpinned packages (fails, matching, distribution)

    hooks/sg-python.sh:166 · skill_risk:S2

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

One version so far: v1 (2.0.17), seen 2026-11-03.

Files

Files

61 files, 997 KB in total. Names only; open them on GitHub.

  • .claude-plugin/plugin.json
  • LICENSE
  • README.md
  • hooks/_base.py
  • hooks/diffstate.py
  • hooks/ensure_agent_sdk.py
  • hooks/extensibility.py
  • hooks/gitutil.py
  • hooks/hooks.json
  • hooks/llm.py
  • hooks/patterns.py
  • hooks/reporesolve.py
  • hooks/review_api.py
  • hooks/security_reminder_hook.py
  • hooks/session_state.py
  • hooks/sg-python.sh
  • tests/conftest.py
  • tests/test_add_failure_metric.py
  • tests/test_baseline_lookup.py
  • tests/test_bootstrap_spawn_cwd.py
  • tests/test_custom_headers.py
  • tests/test_diff_parsing.py
  • tests/test_diff_prefix_config.py
  • tests/test_findings_delivery.py
  • tests/test_gateway_sign_in.py
  • tests/test_git_index_locks.py
  • tests/test_inflight_reviews.py
  • tests/test_launcher_newer_python.py
  • tests/test_launcher_probe_timing.py
  • tests/test_launcher_process_count.py
  • tests/test_launcher_unreadable_script.py
  • tests/test_nested_repos.py
  • tests/test_network_failure_class.py
  • tests/test_no_credentials_notice.py
  • tests/test_notebook_edit_patterns.py
  • tests/test_pattern_fired_metrics.py
  • tests/test_patterns_file_shape.py
  • tests/test_portable_output.py
  • tests/test_prompt_cache.py
  • tests/test_prompt_untracked_snapshot.py
  • tests/test_repeated_diff_count.py
  • tests/test_repo_resolution.py
  • tests/test_review_model.py
  • tests/test_review_outcomes.py
  • tests/test_review_usage_log.py
  • tests/test_reviewer_context_metrics.py
  • tests/test_reviewer_tools.py
  • tests/test_sdk_bootstrap_switches.py
  • tests/test_sdk_emptied_install.py
  • tests/test_secret_named_metric.py
  • tests/test_secret_shaped_paths.py
  • tests/test_slow_prompt_metrics.py
  • tests/test_state_file.py
  • tests/test_stop_baseline_checkout.py
  • tests/test_stop_diff_memory.py
  • tests/test_stop_review_paths.py
  • tests/test_stop_scope_metrics.py
  • tests/test_temp_index_cleanup.py
  • tests/test_tls_store_unreadable_cert.py
  • tests/test_untracked_cap.py
  • tests/test_user_config_dir.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.

Book a demo

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 security skills and plugins

See all