prompt injection commands

Agent-Threat-Rule/agent-threat-rules

Command Claude Code

Open GitHub issues on flagged repos to notify authors before public disclosure.

Agent-Threat-Rule/agent-threat-rules

Command Claude Code

Scan the most popular MCP skills to find issues in well-known packages. This is the highest-value content for Skills Sec.

Agent-Threat-Rule/agent-threat-rules

Command Claude Code

Show current status of the scanning pipeline and content queue.

superagent-ai/brin

Command

Scan a package, repo, MCP server, domain, web page, or skill for security threats using the brin API.

MaxwellCalkin/sentinel-ai

Command

Check text or a file for personally identifiable information and show the redacted version.

MaxwellCalkin/sentinel-ai

Command

Generate a detailed safety risk report for the current conversation or a specific file.

MaxwellCalkin/sentinel-ai

Command

Red-team your safety scanning by generating adversarial variants of a prompt injection attempt.