Autonomous GitHub Team

Autonomous GitHub Team — 41 AI agents that autonomously monitor a GitHub repository, detect bugs, create fixes, open PRs, and release to production. Triggers...

Security Scan

The skill's requirements and instructions align with its stated purpose (autonomously operating on a GitHub repo), but it is high-risk because it clones and executes third‑party scripts and requires a write-scoped GitHub token — audit and sandbox before use.

Purpose & Capability

Name/description, required binaries (git, bash, curl, python3), and required env vars (GH_TOKEN, TARGET_REPO) are coherent for an autonomous GitHub automation that clones a repo and runs orchestrator scripts. Declared permissions (repo/PR/issues write) match the described functionality.

Instruction Scope

SKILL.md explicitly instructs cloning a remote repository and running orchestrator and agent shell scripts (agents/orchestrator.sh). While this is within the stated purpose, it directs execution of third‑party code with a write-capable PAT — a direct data-exfiltration or supply-chain risk. The skill does advise auditing agent scripts and running in a fork, but the runtime instructions inherently grant broad discretion to those remote scripts.

Install Mechanism

There is no packaged install; the skill is instruction-only and instructs git-cloning https://github.com/captainsvbot/AutonomousGitHubTeam.git pinned to tag v1.0.0. Cloning from GitHub and pinning a tag is better than downloading from an arbitrary server, but it still results in executing remote code on the host — a significant risk.

Credentials

Requested environment variables (GH_TOKEN and TARGET_REPO) are necessary for repository operations the skill performs. The GH_TOKEN requires write scopes, which are proportionate to creating fixes, PRs, and releases, but this is high privilege — the skill itself and its instructions repeatedly warn to use a least-privilege, repo-scoped token.

Persistence & Privilege

The skill does not request always:true or any system config paths and is user-invocable; however, because the agent can run autonomously (platform default) and the skill uses a write-capable PAT, an autonomous run could perform actions in the target repo without manual intervention. The SKILL.md recommends human review before merging, but you should confirm any automated merge/rollback behaviors in the repo code before enabling autonomous runs.

Assessment

This skill is internally consistent with its goal but is high-risk: it clones and executes third-party scripts and needs a write-capable GitHub token. Before installing, do all of the following: (1) Inspect the pinned v1.0.0 tag contents (especially agents/*.sh) and confirm what network calls and token usage occur; (2) Create a fine‑grained PAT scoped only to a single test repository (avoid org- or account-wide scopes) and prefer short expiration; (3) Test in an isolated fork or disposable repository first, with branch protection on main; (4) Run with a read-only or minimally scoped token initially to observe proposed changes without allowing writes; (5) Ensure human approval gates exist before any merge to main; (6) Monitor activity and rotate the token after testing. Because this package is instruction-only (no embedded code in the registry), you cannot rely on the registry scan — manual code review of the cloned repository is essential. If you cannot audit the code yourself, treat the skill as unsafe for production repositories.

🤖 Autonomous GitHub Team Skill

⚠️ Security Warning — Read Before Installing

This skill clones and executes bash scripts from a remote repository. Before running:

1. Audit the scripts first — review every agent file in the agents/ directory
2. Use a least-privilege PAT — dedicated token scoped to a single test repo, not your main account
3. Never run on a production repo until you've tested in an isolated fork
4. Never commit tokens — keep config.env private and out of version control
5. Require human review before merging any PRs the agents create

What It Does

41 AI agents that autonomously monitor a GitHub repository, detect bugs, create fixes, open PRs, and release to production automatically.

Required Environment Variables

GH_TOKEN        # GitHub PAT — needs: contents:w, pr:w, issues:w
TARGET_REPO     # The repository to operate on (format: owner/repo)

Primary credential: GH_TOKEN — treat this as a high-privilege secret.

Setup

# 1. Clone the repo (pinned to v1.0.0 tag)
git clone --branch v1.0.0 https://github.com/captainsvbot/AutonomousGitHubTeam.git
cd autonomous-github-team

# 2. Configure — edit config.env
cp config.example.env config.env
nano config.env   # set GH_TOKEN and TARGET_REPO

# 3. Audit the agents first (important!)
# Review agents/*.sh before running anything

# 4. Run
bash agents/orchestrator.sh

Security Requirements for the GitHub Token

The skill needs a token that can:

• Read and write to repository contents
• Create and manage pull requests
• Read and write issues

Create a dedicated token for this skill:

1. GitHub → Settings → Developer Settings → Personal Access Tokens → Fine-grained tokens
2. Scope to only the specific repository you want the team to operate on
3. Grant only: contents: read and write, pull requests: read and write, issues: read and write
4. Never use your main account token with broad org access

Available Agents

bash agents/orchestrator.sh          # Full pipeline (detect → fix → release)
bash agents/security-agent.sh        # Vulnerability scanning
bash agents/fixer-agent.sh          # Apply fixes, open PRs
bash agents/git-guardian-agent.sh     # Merge PRs (requires human review before main merges)
bash agents/backup-agent.sh          # Backup repo via GitHub API
bash agents/rollback-agent.sh         # Auto-revert broken commits
bash agents/team-bravo.sh            # Activity monitor (read-only check)

Gitflow

feature/fix → develop → main

Every run syncs main → develop first. The Git Guardian does not auto-merge to main — all merges to main require human approval.

Before Running on a Production Repo

• Clone and review all agents/*.sh files
• Test in an isolated fork first
• Set up branch protection on main (require PR reviews)
• Use a dedicated, scope-limited PAT
• Keep config.env out of version control

Security Checklist Before Publishing Changes

# Scan for accidentally committed secrets
grep -rni "gho_\|token\|secret\|api_key\|password" .

If you modify this repo, always scan before pushing publicly.