Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Giga Coding Agent
v1.0.0Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
⭐ 0· 1.7k·14 current·16 all-time
by@branexp
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description match the instructions: the skill is an instruction cookbook for running Codex, Claude, OpenCode, or Pi as background processes. However the SKILL.md assumes additional tools (git, gh, pnpm/pnpm install, tmux, mktemp, a 'bash' skill dispatch mechanism) and access to GitHub/git credentials that are not listed in the registry requirements. Those omissions make the declared requirements incomplete, though not necessarily malicious.
Instruction Scope
The instructions include cloning repos, running agents with flags that auto-approve or bypass sandboxes (e.g. --yolo / --dangerously-bypass-approvals-and-sandbox), committing and pushing changes, and using gh pr comment — all of which can modify remote repositories and require credentials. The SKILL.md also references reading ~/.codex/config.toml for defaults. While this is within the broad purpose (automated coding), it grants the running agent potentially wide filesystem and network effects; the doc does not limit or explicitly require confirmation steps before destructive actions.
Install Mechanism
This is instruction-only (no install spec) which is lower risk in that nothing is written by default. The SKILL.md does include an example that installs the Pi agent via 'npm install -g', but does not provide an install spec or verify sources. Relying on local package managers (npm/pnpm) and global installs is expected but not fully specified.
Credentials
The registry lists no required environment variables, but the instructions implicitly rely on credentials and environment state: git or gh authentication (SSH keys or GITHUB_TOKEN), npm authentication for package installs, and optional API keys for Pi (it mentions env var defaults for API key). The skill does not declare or warn about requiring these secrets, so users might unintentionally expose or use credentials when running the recommended commands.
Persistence & Privilege
The skill does not request always:true, has no install step that persists code, and is instruction-only. It does instruct running background agents and using other skills (bash, tmux) but does not claim persistent elevated privileges over the system or other skills.
What to consider before installing
This skill is basically a cookbook for running third‑party coding CLIs in background mode — that is coherent with its description, but it presumes you have and are willing to use git/gh/ssh or token credentials, pnpm/npm, and the agent CLIs. Before installing or using it: (1) Confirm you trust the CLIs (codex/claude/opencode/pi) you will run; (2) Never use flags like --yolo (they bypass safety sandboxes); (3) Be explicit about which credentials (GitHub token, SSH key, API keys) are present in your environment and avoid running in your live project folder; (4) Prefer cloning to a temporary directory and inspect commands before letting any agent auto-commit/push; (5) Ask the publisher to list all required binaries and credentials (git, gh, pnpm, tmux, and any API keys) and to remove or clearly warn about unsafe flags. If you cannot confirm those, treat the skill as risky and run its commands manually under supervision rather than allowing autonomous invocation.Like a lobster shell, security has layers — review code before you run it.
latestvk97ac2736qg808y8vn8gr4pjhs8101dy
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧩 Clawdis
Any binclaude, codex, opencode, pi