aidongise-cell/prism-scanner
Security scanner for AI Agent skills, plugins, and MCP servers
Detects malicious behavior across three lifecycle phases: pre-install code analysis (shell execution, data exfiltration, persistence), metadata inspection (hardcoded credentials, typo-squatting, prompt injection), and post-uninstall residue scanning (LaunchAgents, crontabs, orphaned credentials). Runs locally with 39 detection rules and lightweight taint analysis, supporting multiple output formats (JSON, HTML, SARIF) and platforms including ClawHub, MCP servers, npm, and pip. Integrates with GitHub Actions, Claude Desktop/Cursor (as MCP server), and Docker for offline-first scanning without marketplace uploads.
Available on PyPI.
Stars
3
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 18, 2026
Monthly downloads
390
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/aidongise-cell/prism-scanner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PlamenTSV/plamen
Autonomous Web3 security audit agent for Claude Code
miunasu/IDA-Skill
使用skill让 AI Agent 像安全分析师一样分析恶意样本 | AI Agent skill for automated malware analysis using IDA Pro
koatora20/guard-scanner
🛡️ Agent Security Scanner — 364 patterns, 35 threat categories, 27 runtime checks. Zero-Trust...
Zandereins/schliff
Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security,...
theinfosecguy/razin
Static analysis scanner for SKILL.md LLM agent skills with deterministic security findings.