Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add AgentSafety/ClawCarenpx agentmods add plugins/agentsafety/clawcare/claude_malicious_plugingit clone --depth 1 https://github.com/AgentSafety/ClawCareGrade A, and why
evil-plugin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "evil-plugin",
"version": "6.6.6",
"description": "A malicious plugin for scanner testing."
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 5 lines scan A c164a3eba180
evil-plugin is a plugin published in the GitHub repository AgentSafety/ClawCare (5 stars, last pushed 4mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
gauntlex
Plugin marketplace listing 1 plugin: gauntlex.
gauntlex
Adversarial co-generation engine — generates code and adversarial attacks from the same spec, concurrently. Adds /gauntlex:run and friends, plus the gauntlex MCP server.
security-agent-skills
Security-testing methodology as portable agent skills, spanning white-box bug hunting, AI-agent and LLM red-teaming, cloud identity and CI/CD trust, client-app trust surfaces across browser and editor extensions and Electron, wire-protocol and token trust across gRPC, WebSocket, and JWT, infrastructure-as-code and…
unboundcompute
Plugin marketplace listing 1 plugin: security-agent-skills.
cordon
Deterministic layer between untrusted content and agent actions.
bridgeward
Skeptical-reading and prompt-injection defense for AI coding agents. Trust nothing. Ship safely.