1,850,287 packages matching “data-exfiltration”
@mondaydotcomorg/atp-provenance
v0.22.3 · 4 months ago
CAMEL-inspired provenance security for LLM applications - track data origin and enforce security policies
No known vulnerabilities
capscope
v0.6.0 · 1 month ago
Capability auditor for AI agents. Scans tool definitions from LangChain, OpenAI, MCP and more — detects dangerous capability combinations before they reach production.
No known vulnerabilities
opencode-bash-classifier
v0.5.1 · 1 month ago
Execution-boundary command safety classifier for OpenCode's native Bash tool: static per-segment review plus a tool-enhanced OpenAI-compatible model reviewer.
No known vulnerabilities
@log.li/dsh-automode
v0.15.3 · 6 days ago
CC-style auto mode for DeepSeek Harness: deterministic deny/allow rules + pre-execute gate + model-agnostic two-stage classifier. Two-state (allow/reject) classifier since 0.8.0. TypeScript rewrite merging dsh-auto-mode v0.4.1 with Nuo-cl/dsh-auto-mode na
No known vulnerabilities
mailwarden
v0.22.0 · 4 days ago
A reliable, native Gmail MCP server with full mailbox control — search, labels, archive, trash, attachments, and snooze.
No known vulnerabilities
@nodesecure/js-x-ray
v16.1.0 · 5 days ago
JavaScript AST XRay analysis
No known vulnerabilities
nsauditor-ai
v0.2.54 · 6 days ago
Modular AI-assisted network security audit platform — Community Edition
No known vulnerabilities
@opena2a/aicomply
v2.2.3 · 1 month ago
Inline PII, credential, and regulated-data classifier for AI agent I/O. Dual-layer: deterministic regex + optional semantic Guard. Library + CLI.
No known vulnerabilities
acurist
v1.2.5 · 2 days ago
The ultimate penetration testing agent
No known vulnerabilities
@enclave-vm/core
v2.15.2 · 1 month ago
Sandbox runtime for secure JavaScript code execution
No known vulnerabilities
codegate-ai
v1.4.2 · 20 days ago
Pre-flight security scanner for AI coding tool configurations.
No known vulnerabilities
@weave_protocol/mund
v0.2.3 · 3 months ago
The Guardian Protocol - MCP-based security monitoring for agentic AI systems
No known vulnerabilities
fullcourtdefense-cli
v1.35.7 · 1 day ago
Full Court Defense CLI — security scanning for AI agents from your terminal
No known vulnerabilities
@goplus/agentguard
v1.1.29 · 27 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
agentverus-scanner
v0.8.1 · 2 months ago
AgentVerus skill trust scanner — security and behavioral analysis for AI agent skills
No known vulnerabilities
@strixgov/capabilities-mcp-common
v0.1.2 · 1 month ago
Pre-classified capability registry for popular MCP servers (Slack, GitHub, Linear, Notion, Filesystem, Postgres, Email/SMTP/Gmail). Drop-in starter for @strixgov/tool-gateway.
No known vulnerabilities
jev-axi
v0.7.0 · 3 days ago
Agent-ergonomic CLI for TypeSafe's Jev: offload snap judgments (choice, score, yes/no) over files and stdin to a fast calibrated model.
No known vulnerabilities
@node9/policy-engine
v2.19.2 · 4 hours ago
Shared policy evaluation engine for node9 — DLP, smart rules, AST shell parsing, shields, loop detection. Pure functions, no I/O. Used by both node9-proxy and the node9 SaaS firewall.
No known vulnerabilities
@panguard-ai/panguard
v1.9.0 · 1 month ago
Panguard AI - Unified security CLI
No known vulnerabilities
@agentvault/claude-bridge
v0.8.16 · 9 days ago
AgentVault Claude Bridge — daemon for bridging a Claude agent into secure E2E-encrypted AgentVault 1:1 direct messages and rooms.
No known vulnerabilities