{"data":{"slug":"prismorsec-prismor","name":"prismor","tagline":"Runtime firewall for AI agents to prevent rogue tool calls and security breaches","github_url":"https://github.com/PrismorSec/prismor","owner":"PrismorSec","repo":"prismor","owner_avatar_url":"https://avatars.githubusercontent.com/u/236515725?v=4","primary_language":"Python","stars":343,"forks":35,"topics":["agent-control-plane","agent-security","agents","ai-agents","ai-governance","ai-safety","ai-security","claude-code","control-plane","cybersecurity","devsecops","llm-security","mcp","owasp","prompt-injection","secrets-management","security","skill-scanner","supply-chain-security","tool-calls"],"archived":false,"github_pushed_at":"2026-09-11T05:58:15+00:00","maintenance_label":"Very active","stars_delta_30d":63,"url":"https://www.graphcanon.com/tools/prismorsec-prismor","markdown_url":"https://www.graphcanon.com/tools/prismorsec-prismor.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/prismorsec-prismor","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=prismorsec-prismor","description":" 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.)","homepage_url":"https://prismor.dev","license":"Apache-2.0","open_issues":46,"watchers":4,"ai_summary":"Prismor is a runtime firewall designed to detect and mitigate security threats like dangerous commands, secret leaks, and prompt injection attacks on various AI frameworks including Claude Code, Codex.","readme_excerpt":"## Quick Start (30s)<a name=\"quick-start\" />\n\n```bash\npip install prismor\nprismor setup\n```\n\nFor the Skill, curl, and git-clone alternatives, plus PEP 668 systems and secret-cloaking setup, see the [full installation guide](docs/installation.md).\n\n---","github_created_at":"2026-02-20T16:43:19+00:00","created_at":"2026-07-15T10:42:42.645608+00:00","updated_at":"2026-09-20T04:25:52.719318+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"agent-security","name":"agent-security"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"llm-security","name":"llm-security"},{"slug":"prompt-injection","name":"prompt-injection"},{"slug":"security-tools","name":"security-tools"}],"trust":{"provenance":{"is_fork":false,"github_id":1162750276,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-11T06:00:52.948Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-11T05:58:43Z","stars_delta_30d":63,"open_issues_delta_30d":34},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:42:44.076Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-11T06:00:53.409Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-11T06:00:53.409Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-11T06:00:53.409Z"},"languages":{"value":["python","javascript"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-09-11T06:00:53.409Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-11T06:00:53.409Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free with a commercial license for advanced features."},"requirements":{"min_ram_gb":1,"requires_docker":false},"constraints":{"min_ram_gb":1,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you need a dedicated firewall for AI tools to block unauthorized calls.","If your project involves Claude Code or Codex and requires enhanced security measures."],"when_not_to_use":["Avoid if you do not use supported frameworks like Claude Code or Codex, as it might lack coverage.","Not suitable if you prioritize open-source contributions over runtime protection."],"source":"enrich:decision_facts","observed_at":"2026-07-17T04:12:38.593Z"},"constraint_facets":{"min_ram_gb":1,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Free with a commercial license for advanced features."},{"label":"Requirements","value":"Min 1 GB RAM"},{"label":"Adopt for","value":"Prismor is a runtime firewall that safeguards AI frameworks against security breaches like prompt injection attacks and secret leaks. It supports Claude Code and Codex."},{"label":"License detail","value":"Apache-2.0, permissive open-source license allowing free use and distribution under certain conditions."}]}}