1. Conduid
  2. Security
  3. Promptsentry
MCP server · Security

Promptsentry

by · github.com/younesrest/promptsentry

Scan repos for AI agent supply-chain attacks: invisible Unicode payloads, prompt injection in CLAUDE.md/AGENTS.md/.cursorrules and risky MCP configs. Zero deps, SARIF, GitHub Action.

Unclaimed ai-securityblue-teamdevsecopsmcpprompt-injectionsecuritysupply-chain
InstallView source
34Low

Scored 9 hours ago · breakdown

About Promptsentry

Promptsentry is an MCP server published by younesrest in the Security category: scan repos for AI agent supply-chain attacks: invisible Unicode payloads, prompt injection in CLAUDE.md/AGENTS.md/.cursorrules and risky MCP configs. Zero deps, SARIF, GitHub Action.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/younesrest/promptsentry

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Promptsentry

Powered by Claude · Grounded in docs

I know everything about Promptsentry. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Promptsentry

How do I install Promptsentry?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Promptsentry safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Promptsentry still maintained?

Yes — the last commit was 7 days ago. The repository has 0 stars and 0 forks.