All mods / singh-ap/awesome-claude-mods
injection-guard
SAFE★ 1 by awesome-claude-mods Repository ↗ Mod source ↗
Description
Defuses prompt injection in tool output: strips invisible Unicode that hides text from you but not from the model, and flags web pages, files and command output that carry instructions aimed at Claude.
What it can do
Reach level 0 — draws and remembers What does this mean? →
Can see: every tool call
Raw API calls (4)
- $.command.register
- $.store.get
- $.store.set
- $.ui.toast
Static check passed on Claude Code 2.1.295.
Install
$/plugin marketplace add singh-ap/awesome-claude-mods $/plugin install injection-guard Check the repo for the exact name.
Details
- Repository
- singh-ap/awesome-claude-mods
- Path in repo
- mods/safety/injection-guard
- License
- MIT
- Last updated
- Oct 8, 2026
- First seen
- Oct 10, 2026
- Last scanned
- Oct 10, 2026
Related mods — reach level 0
- codex-memory-plugin ★ 39,271
- protected-paths-guard ★ 32,551
- npm-to-pnpm-rewriter ★ 32,551
- tool-timing-badge ★ 32,551
Capability data is machine-generated by static analysis and may be incomplete. A SAFE badge is not a guarantee — read the code before installing anything with broad access. Not affiliated with Anthropic.
Found a mistake in this listing or verdict? Report an issue →