bradygaster/squad is a tool that creates a human-directed team of AI development agents inside a project repository through GitHub Copilot. Developers use it to delegate work among persistent specialists such as frontend, backend, testing, and lead agents while retaining responsibility for decisions and review. The catalogue entries are the skills, agents, and instructions that define and coordinate those team members.
Borrowing it
Nothing to install: this file belongs to bradygaster/squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bradygaster/squad/dev/.copilot/skills/security-review/SKILL.mdgit clone --depth 1 https://github.com/bradygaster/squadWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bradygaster/squad/security-review)<a href="https://agentmods.dev/skills/bradygaster/squad/security-review"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/security-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bradygaster/squad/security-review"><img src="https://agentmods.dev/badge/skills/bradygaster/squad/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 97 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Tool Misuse · line 114 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 156 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 156 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 156 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 156 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Excessive Agency · line 156 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 213 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.02669 |
| Opus 5.5 | $0.00010 | $0.01068 |
| Sonnet 5.5 | $0.00005 | $0.00534 |
| Haiku 4.5 | $0.00002 | $0.00267 |
Grade B, and why
security-review scanned grade B with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
A message containing "; rm -rf /" would execute arbitrary commands. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
A message containing "; rm -rf /" would execute arbitrary commands. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fetch(url, { headers: { Authorization: `Bearer ${apiKey}` } }); Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Child process execution (`child_process.exec`, `child_process.spawn`) How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Every PR that touches authentication, credentials, environment variables, file system operations, child process execution, user input handling, GitHub API calls, or workflow files must be reviewed for security. This skill provides a systematic checklist for catching security issues before they reach production.
Use this skill when a PR includes any of:
- Changes to
.github/workflows/files - New or modified environment variable usage
- File system read/write operations driven by user input
- Child process execution (
child_process.exec,child_process.spawn) - GitHub API calls (Octokit,
ghCLI wrappers) - New npm dependencies
- Credential or token handling
- Template rendering with dynamic values
Patterns
1. Secrets and Credentials
No secrets in source code — ever.
Review checklist:
- ❌ No API keys, tokens, passwords, or connection strings in committed files
- ❌ No hardcoded
GITHUB_TOKEN,NPM_TOKEN, or similar values - ❌ No
.envfiles committed (verify.gitignorecovers them) - ✅ Secrets must be referenced via
process.env.Xor${{ secrets.X }}in workflows - ✅ If the PR adds a new secret reference, verify it's documented in setup instructions
Watch for disguised secrets:
- Base64-encoded strings that decode to tokens
- URLs with embedded credentials (
https://user:token@host) - Test fixtures that contain real credentials from copy-paste
2. Personal Data in Committed Files
Personal data (especially email addresses) must never be written to committed files.
Squad-specific rule: git config user.email is explicitly banned from being written to any file that gets committed. This prevents PII leakage into the repository.
Review checklist:
- ❌ No email addresses written to committed files (even in config generation)
- ❌ No
git config user.emailoutput captured and stored in source - ✅ If user identity is needed at runtime, read it dynamically and never persist to a committed file
3. Environment Variable Safety
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 267 lines · 24 tokens per session scan B 1bc789a46d65
security-review is a skill published in the GitHub repository bradygaster/squad (3,295 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,669 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 4 findings (unrestricted tool access, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ponytail-review
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this…
ponytail-audit
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find…
omk-code-review
Review implementation changes against contracts and real failure modes, preserve minimal patches, and verify regressions without confusing test counts, generated code volume or CI claims with production correctness.
ralphctl-code-review-and-quality
Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when acting as the evaluator assessing a generator's output, and when reviewing any change before signalling…
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
ce-code-review
Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked for review; interactive mode can fix locally, while mode:agent reports only for pipeline callers.