Claude Code, Skill
Everything Copilot Cli
A Copilot-first operating kit for GitHub Copilot CLI: 109 skills, 8 custom agents, rules, MCP presets, and multi-AI orchestration patterns.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High finding. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 35117910be57, unchanged since the check below.
INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL
Why this grade
- INSTALL_REMOTE_SCRIPT Medium
Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).
guides/the-quickstart-guide.md, line 36
curl -fsSL https://gh.io/copilot-install | bash - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
skills/security/secret-detection/SKILL.md, line 53
git --no-pager ls-files | Select-String "\.pem$|\.key$|\.p12$|\.pfx$|id_rsa|\.env$"
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
orchestration/skills/multi-ai-handoff.md, line 247
Invoke-Expression "codex exec '$issueBody'" # do not do this either
orchestration/patterns/message-ipc.md, line 197
subprocess.run([
orchestration/skills/multi-ai-handoff.md, line 234
interpreter (`Invoke-Expression`, `cmd /c`, `bash -c`, or similar). Untrusted text
Show more
skills/security/pr-security-review/SKILL.md, line 204
- `eval()`, `exec()`, or `child_process.spawn()` added with user input
Install and update
Serious
install fetches a script from the network.
INSTALL_REMOTE_SCRIPT
guides/the-quickstart-guide.md, line 36
curl -fsSL https://gh.io/copilot-install | bash
Network
Concern
can reach a host that is not written as a fixed address.
NETWORK_NO_FIXED_HOST
skills/documentation/api-documentation/SKILL.md, line 128
curl -s http://localhost:3000/api/health | python -m json.tool
skills/testing/e2e-testing/SKILL.md, line 61
curl -s http://localhost:3000/health
skills/testing/test-coverage/SKILL.md, line 140
const result = await apiClient.fetch('/endpoint', { fetch: mockFetch });
Show more
skills/testing/test-coverage/SKILL.md, line 147
await expect(apiClient.fetch('/endpoint', { fetch: mockFetch }))
rules/frameworks/nextjs.md, line 21
- Use `fetch()` with `cache` / `revalidate` options in Server Components for ISR
skills/security/security-bounty-hunter/SKILL.md, line 63
grep -r "requests.get\|urllib\|fetch\|axios" src/ --include="*.py" --include="*.ts" -n
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
agents/doc-updater.md, line 147
4. Update .env.example with new variables
agents/security-reviewer.md, line 138
2. Check .env files, config files, docker-compose files
skills/security/secret-detection/SKILL.md, line 53
git --no-pager ls-files | Select-String "\.pem$|\.key$|\.p12$|\.pfx$|id_rsa|\.env$"
Show more
skills/copilot-exclusive/agentic-engineering/SKILL.md, line 118
verifies with the secret in process.env.JWT_SECRET, attaches user to req.user.
skills/development/nestjs-prisma/SKILL.md, line 127
# 3. Add DATABASE_URL to .env
skills/development/nextjs-prisma/SKILL.md, line 88
# 2. Add DATABASE_URL to .env
skills/security/evaluate-repository/SKILL.md, line 51
Get-Content .gitignore | Select-String "\.env|\.pem|\.key|secret"
skills/security/evaluate-repository/SKILL.md, line 215
║ Secrets & Credentials ║ 7/10 ║ .env.example checked in, no actuals ║
skills/security/secret-detection/SKILL.md, line 46
grep -rni "jwt[_]?secret\|signing[_]?key" src/ --include="*.ts" | grep -v "process\.env\|config\."
skills/security/secret-detection/SKILL.md, line 83
const apiKey = process.env.API_KEY;
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Concern
contains an encoded blob in a file that should be readable.
OBFUSCATION_ENCODED_BLOB
docs/images/badge-copilot-cli-ready.svg, line 1
<svg xmlns="http://www.w3.org/2000/svg" width="121" height="20" role="img" aria-label="copilot-cli: ready"><title>copilot-cli: ready</title><linearGradient id="s" x2="0" y2="100%">
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 35117910be57. requests shell access. The manifest names this permission. install fetches a script from the network. can reach a host that is not written as a fixed address. reads a credential or environment file. contains an encoded blob in a file that should be readable.
Date and source
Date checked:
github.com
Commit graded: 35117910be5703d2a094ef35cf8830b07b980228
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.