2,935 packages matching “dangerous”
@yottameta/yotta-guardian
v0.1.5 · 19 hours ago
Yuandun (元盾) — cross-agent dangerous tool-call guardrail: a deterministic rule engine + pluggable intent verifier (model-agnostic) that evaluates exec/write/edit/read/run/shell calls and provides audit logs. Triggers when an agent is about to run a high-r
No known vulnerabilities
@inobit/pi-permission
v1.1.1 · 25 days ago
Lightweight permission enforcement extension for the Pi coding agent: sensitive-file guard, read/write-aware project boundary, dangerous-operation confirmation, and plan/build read-only mode.
No known vulnerabilities
@diegopetrucci/pi-permission-gate
v0.1.14 · 18 days ago
A pi extension that prompts before dangerous shell commands and protected file writes.
No known vulnerabilities
@firstpick/pi-extension-safety-guard
v0.3.0 · 2 days ago
Interactive guardrails for dangerous bash commands and protected file edits in Pi.
No known vulnerabilities
@goplus/agentguard
v1.1.29 · 25 days ago
GoPlus AgentGuard — Security guard for AI agents. Blocks dangerous commands, prevents data leaks, protects secrets. 20 detection rules, runtime action evaluation, trust registry.
No known vulnerabilities
@yassimba/pi-guardrails
v0.20.0 · 2 days ago
Security guardrails for Pi: protected paths, workspace boundaries, and dangerous-command gates.
No known vulnerabilities
@kreeger/pi-safe-command
v0.2.0 · 2 days ago
Prompts for confirmation before running dangerous commands in the pi-coding-agent.
No known vulnerabilities
@framers/agentos-ext-code-safety
v0.2.1 · 4 months ago
Static analysis guardrail for detecting dangerous code patterns in AgentOS
No known vulnerabilities
@dangerousthings/web
v0.7.0 · 4 days ago
Web CSS theme for the Dangerous Things design system — bevels, glows, form styles
No known vulnerabilities
opencode-damage-control
v1.5.0 · 6 months ago
OpenCode plugin that blocks dangerous commands and protects sensitive paths
No known vulnerabilities
@elite-dangerous-plugin-framework/journal
v0.20260214.1 · 7 months ago
Autogenerated Elite: Dangerous Journal Event definitions as TypeScript Types
No known vulnerabilities
dangerous-shop
v1.0.0 · 2 years ago
dangerous-shop
No known vulnerabilities
@kayahr/ed-journal
v3.9.1 · 5 months ago
Typescript library to read/watch the player journal of Frontier's game Elite Dangerous
No known vulnerabilities
@stroq/cli
v0.13.0 · 3 days ago
Local action firewall for AI agents: scans what the agent reads, taints the session, blocks dangerous follow-up actions
No known vulnerabilities
dangerous-html
v0.1.13 · 3 years ago
A simple custom-element to render html using lit-html.
No known vulnerabilities
@agentx-core/scan
v0.5.0 · 20 days ago
List the tools your AI agent can call, ranked by how dangerous they are, and which are unguarded.
No known vulnerabilities
@saferun/cli
v0.6.63 · 7 months ago
AI Safety Middleware - Protect your Git workflows from dangerous AI agent operations
No known vulnerabilities
@pi-harness/plugin-secure-audit
v0.1.33 · 6 days ago
Read-only workspace scan for exposed credentials and dangerous shell commands with value-redacted findings.
No known vulnerabilities
c1ebe751dedf
v0.1.10015 · 2 years ago
dangerous
No known vulnerabilities
eslint-plugin-unicode-comments
v2.1.3 · 1 month ago
ESLint plugin flagging dangerous Unicode characters (Trojan Source, homograph attacks) and typographic tells of unedited AI-generated code (em dashes, curly quotes, ellipsis, non-breaking spaces)
No known vulnerabilities