RedPincer — AI Red Team Suite

AI/LLM red team testing skill. Point at any LLM API endpoint and run automated security assessments. 160+ attack payloads across prompt injection, jailbreak,...

This skill appears to be a red-team tool but contains several red flags you should address before running it: 1) Verify provenance — the registry entry lacks a homepage and source is 'unknown'; inspect the GitHub repo (https://github.com/rustyorb/pincer) yourself. 2) Do not run npm ci / npm run dev until you review package.json and all scripts and dependencies; run in an isolated environment (container or VM) and as a non-root user. 3) The SKILL.md uses git clone but metadata does not list git as required — ensure your environment matches actual instructions or adjust the instructions. 4) The doc claims 'all client-side' but instructs starting a Next.js server (npx next start -H 0.0.0.0) — confirm whether API keys are ever proxied server-side and avoid binding to 0.0.0.0 on untrusted networks; prefer localhost-only or a browser-only build. 5) If you must test, run initial scans (npm audit, static analysis) and host the app in a sandbox before supplying any real API keys; consider using throwaway keys or scope-limited accounts. 6) Ensure you have explicit authorization to test any target systems; this tool is for authorized testing only. If you want a safer evaluation, provide the repository URL and package.json so the code can be reviewed for network calls, telemetry, and server-side behavior.

Type: OpenClaw Skill Name: redpincer Version: 1.0.0 The skill bundle is classified as suspicious because it instructs the OpenClaw agent to install a 'red team testing skill' (RedPincer) via `git clone` and `npm ci` commands specified in `SKILL.md`. While the `SKILL.md` explicitly states the tool is 'For authorized security testing and research only' and claims API keys stay local, the installed tool's capabilities include 'prompt injection, jailbreak, data extraction, and guardrail bypass' against target LLMs. The installation process itself involves shell execution, network access (to GitHub and npm registry), and file system modifications, which are risky capabilities. Although there's no direct evidence of malicious intent from the skill bundle's instructions (e.g., exfiltrating user data or prompt injection against the OpenClaw agent), the installation of a powerful red-teaming tool with such capabilities warrants a 'suspicious' classification due to the inherent potential for misuse and the broad system permissions required for its setup.