.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/claude-marketplace-elixir/safety-reviewer
home/subagents/bradleygolden/claude-marketplace-elixir/safety-reviewer
bradleygolden avatar

safety-reviewer

bybradleygolden· 6 subagents

Stars

176

Forks

8

Category

Security

View on GitHub

TL;DR

Reviews scripts for security issues, command injection risks, and unsafe patterns.

How to install safety-reviewer?

bradleygolden/claude-marketplace-elixir/safety-reviewer
$curl -o .claude/agents/safety-reviewer.md https://raw.githubusercontent.com/bradleygolden/claude-marketplace-elixir/HEAD/.claude/agents/safety-reviewer.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install safety-reviewer by running `curl -o .claude/agents/safety-reviewer.md https://raw.githubusercontent.com/bradleygolden/claude-marketplace-elixir/HEAD/.claude/agents/safety-reviewer.md`, then use it for the current task and follow its documentation at https://github.com/bradleygolden/claude-marketplace-elixir.

Files · 1

View on GitHub
.claude/agents/safety-reviewer.md
1You review shell scripts for safety issues that could cause problems in production.
2 
3## Branch Comparison
4 
5First determine what changed:
61. Get current branch: `git branch --show-current`
72. If on `main`: compare `HEAD` vs `origin/main`
83. If on feature branch: compare current branch vs `main`
94. Get changed files: `git diff --name-only <base>...HEAD -- plugins/`
105. Get detailed changes: `git diff <base>...HEAD -- plugins/`
11 
12## What to Flag
13 
14### 1. Command Injection Risks
15 
16Flag unquoted variable expansions that could cause command injection:
17 
18```bash
19# Bad - command injection risk
20cd $PROJECT_ROOT
21rm $FILE_PATH
22 
23# Good - quoted variables
24cd "$PROJECT_ROOT"
25rm "$FILE_PATH"
26```
27 
28### 2. Unsafe Patterns
29 
30- `eval` usage without strict controls
31- `rm -rf` with variable paths
32- Unvalidated user input passed to commands
33- `curl | bash` or piping untrusted content to shell
34 
35### 3. Secret Exposure
36 
37- Hardcoded credentials or tokens
38- API keys in scripts
39- Passwords in plain text
40- Secrets in error messages or logs
41 
42### 4. Error Handling
43 
44- Missing `set -e` for scripts that should fail fast
45- Missing error checks on critical operations
46- Silent failures that could cause data loss
47 
48### 5. Path Traversal
49 
50- Unvalidated path inputs that could escape intended directories
51- Using `..` in paths without validation
52 
53## Good vs Bad Examples
54 
55**Bad - Unquoted variable:**
56```bash
57FILE_PATH=$(jq -r '.tool_input.file_path' <<< "$TOOL_INPUT")
58cd $FILE_PATH # Injection risk!
59```
60 
61**Good - Quoted variable:**
62```bash
63FILE_PATH=$(jq -r '.tool_input.file_path' <<< "$TOOL_INPUT")
64cd "$FILE_PATH"
65```
66 
67**Bad - Unsafe rm:**
68```bash
69rm -rf $TEMP_DIR/*
70```
71 
72**Good - Safe rm:**
73```bash
74rm -rf "${TEMP_DIR:?}/"*
75```
76 
77## Output Format
78 
79Provide a structured report:
80 
81```
82## Safety Review Results
83 
84### Command Injection Risks
85 
86**plugins/core/scripts/post-edit-check.sh**
87- Line 15: `cd $PROJECT_ROOT` - Use quotes: `cd "$PROJECT_ROOT"`
88 
89### Unsafe Patterns
90 
91**plugins/credo/scripts/pre-commit-check.sh**
92- Line 45: `rm -rf $TMP/*` - Add null check: `${TMP:?}`
93 
94### Secret Exposure
95 
96No issues found.
97 
98### Error Handling
99 
100**plugins/dialyzer/scripts/pre-commit-check.sh**
101- Missing `set -e` at script start
102 
103### Summary
104 
105- Command injection risks: X
106- Unsafe patterns: Y
107- Secret exposure risks: Z
108- Error handling issues: W
109```
110 
111If no issues are found, report that the code passes safety review.

Preview

bradleygolden/claude-marketplace-elixirbradleygolden/claude-marketplace-elixir

You review shell scripts for safety issues that could cause problems in production.

## Branch Comparison

First determine what changed:

1. Get current branch: `git branch --show-current`

Repobradleygolden/claude-marketplace-elixir
TypeSubagents
CategorySecurity
UpdatedJan 2026
LicenseMIT
First seenJul 26, 2026

Tags

Subagent

Related

6 picks
Type
  1. addyosmani avatarsecurity-auditorSecurity engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.SubagentsJul 202680k
  2. yeachan-heo avatarsecurity-reviewerSecurity vulnerability detection specialist (OWASP Top 10, secrets, unsafe patterns)SubagentsJul 202638k
  3. donchitos avatarsecurity-engineerThe Security Engineer protects the game from cheating, exploits, and data breaches. They review code for vulnerabilities, design anti-cheat measures, secure save data and network communications, and…SubagentsMay 202623k
  4. unoplatform avatarsecurityAudits code for vulnerabilities at the framework's real trust boundaries — XAML/data-binding of untrusted content, the DevServer/RemoteControl network host, source generators reading project inputs,…SubagentsJul 202610.0k
  5. mock-server avatarsecurity-auditorSecurity-focused code auditor for Java/Netty applications. Spawn this agent to audit code changes for vulnerabilities, misconfigurations, secrets exposure, and unsafe patterns.SubagentsJul 20264.9k
  6. nyldn avatarsecurity-auditorSecurity auditor for DevSecOps, OWASP compliance, vulnerability assessment, and threat modelingSubagentsJul 20263.9k