Skip to main content
skill CX Codex

clawtributor — Claude Code skill: what it does, how to install

clawtributor enables agents to document prompt attacks, sandbox evasions, and dangerous extensions for collective security feeds.

AGPL-3.0 208 installs ★ 1,135 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add prompt-security/clawsec --skill clawtributor -a claude-code
Open on GitHub

What clawtributor does

This skill provides a structured way for agents to record security threats they encounter during execution. It targets adversarial prompt injections, attempts to extract credentials or environment variables, and rogue plugins attempting unauthorized actions.

Operation happens locally without background outbound traffic. The skill creates state and incident files strictly inside ~/.clawsec/clawtributor/, meaning reports remain on your disk until you submit them through an external form.

Because network transmission requires manual user submission, you must clean raw traces of secrets before pasting them to review boards. No automated sync occurs behind the scenes.

What it helps with

  • document prompt injection attacks bypassing agent boundaries
  • draft structured incident files for suspicious plugins
  • preserve attack evidence locally prior to sharing it with maintainers

Example prompts for the agent

  • Draft an incident record describing the prompt injection attempt in the previous turn
  • Log the suspicious behavior of this third-party skill into a local security report

How to install clawtributor

1Skills CLI (Vercel)

npx skills add prompt-security/clawsec --skill clawtributor -a claude-code

2Manually: put the files in place

~/.claude/skills/clawtributor/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/clawtributor/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about clawtributor

How to install clawtributor in Claude Code?

Run npx skills add prompt-security/clawsec --skill clawtributor -a claude-code in your terminal. The configuration is stored at ~/.claude/skills/clawtributor/SKILL.md.

Does clawtributor automatically send incident data over the network?

No. All drafts stay local in ~/.clawsec/clawtributor/. Submissions require the user to manually review the sanitized text and submit it via a browser form.

What event types should be reported with this skill?

It handles prompt injections trying to override safety guidelines, attempts to dump API tokens or files, and packages displaying data exfiltration or excessive permissions.

Similar skills

All skills for Security →

From the same set9

clawsec-suite The clawsec-suite skill monitors ClawSec advisories, verifies signatures, and checks installed skills for affected entries. Use it when security checks need approval gates. CX Codex +1 881installs openclaw-audit-watchdog The openclaw-audit-watchdog skill runs a deep security audit of OpenClaw agents on a schedule and sends the report as a direct message. Email delivery is optional. CX Codex +1 756installs clawsec-clawhub-checker clawsec-clawhub-checker — a skill that vets code before installation by checking ClawHub reputation scores, scanner status, and authorship history. Install it if you want an extra approval layer for skill installs across your environments. CX Codex +1 259installs soul-guardian The soul-guardian skill watches agent workspace files against an approved baseline, restores selected files, and raises alerts when drift appears. CX Codex +1 258installs clawsec-feed clawsec-feed provides a consolidated feed of OpenClaw security advisories and threats. Use it when an agent needs current vulnerability context. CX Codex +1 243installs clawsec-scanner The clawsec-scanner skill checks project dependencies and source code for security issues, and inspects OpenClaw hooks. Use it for a project review or recurring scans. CX Codex +1 195installs clawsec-nanoclaw clawsec-nanoclaw — a skill that monitors vulnerabilities in installed skills before adding them or during regular audits. Guards against compromised dependencies using a signed advisory feed. CX Codex +1 189installs hermes-attestation-guardian hermes-attestation-guardian — a skill that verifies Hermes infrastructure integrity at runtime. Generates signed attestations, compares them against baselines, and detects configuration drift. CX Codex +1 129installs

Project sponsors

Companies that keep this analytics open