PrismorSec / prismor
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
Why this job: says: prompt injection; topics: agent-security, ai-governance, security, ai-security, llm-security, prompt-injection, cybersecurity, ai-safety
What it does
- Prismor covers the policy engine, session logs, security audit, and CLI reference
- Supply Chain covers install-time enforcement, IOC matching, and risk scoring
- Network Isolation covers policy-driven egress control, raw IP detection, and tunnel blocking
- Skill Scanner covers MCP server and skill risk scanning across supported agents
- MCP Guardrails let you block a specific MCP server or tool, or require human approval before the agent calls it, with a policy rule you write yourself
Get started
pip install prismor
prismor setup- Maintenance
- Active
- Last commit yesterday
- Stars
- 481
- +9 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- v1.73.0
- Released 4 days ago
- Built with
- Python
- 91% of the code
Is it looked after?
- Contributors
- 7
- Last 90 days
- Issues
- 84% closed
- 28 still open
- Pull requests
- 570 merged
- 23 waiting
- Releases
- 139
- 30+ in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| NVIDIA / SkillSpector | 25,104 | yesterday | Apache-2.0 | No downloads |
| Tencent / AI-Infra-Guard | 7,449 | today | Apache-2.0 | No downloads |
| asamassekou10 / ship-safe | 872 | 24 days ago | MIT | No downloads |
More: download files, languages, topics and project record
Download files, v1.73.0
- Mac2 files, 2 downloads
- Windows2 files, 2 downloads
- Linux4 files, 4 downloads
Languages
- Python 91%
- HTML 7%
- Shell 1%
- TypeScript <1%
Topics
- cybersecurity
- security
- agent-security
- agents
- ai-security
- skill-scanner
- prompt-injection
- ai-agents
- claude-code
- devsecops
- llm-security
- mcp
Project record
- JobAI security
- StatusFeatured
- Commits1,078
- Forks67
- Watching5
- Stars in 28 days+68
- CreatedFeb 20, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026