claude

security-toolkit

Prompt-injection detection hook with tiered HIGH/LOW confidence and env-var-driven allowlist. Covers MCP tool outputs via the * matcher. (Stable subset; full plugin with git/Desktop-Commander blocking lives in bogheorghiu/ex-cog-dev.)

0 on GitHubby bogheorghiuv0.2.1updated 2 months ago
/

Plugin security-toolkit from marketplace ex-cog in bogheorghiu/ex-cog. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Hooks (1)

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/detect-prompt-injection.sh"

View source on GitHub

More from bogheorghiu/ex-cog

All 4 plugins →

research-toolkit

claude

Investigation protocols, dialectic verification, frame rotation, financial analysis (STONK), video/substack research. Includes financial-mcp.

14 skills · 1 command · 5 agents

0

vasana-system

claude

Pattern recognition across unrelated contexts. Observe, record, test, and browse behavioral patterns. Includes relational-memory and edge-graph MCPs.

11 skills · 1 command · 1 agent · hooks

0

budget-mastery

claude

Budget-conscious agent identity — efficiency as capability, not constraint. Loosely based on BATS framework research.

2 skills · 1 agent

0

Maintain security-toolkit?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins