Tool
promptblock — block prompt injection in GitHub issues
Publication date not yet evaluated · Added ryandens.github.io
Page published
Coverage timeline
Single-source analysis — one report is available.
Why it matters
AI agents that read GitHub issues can be hijacked by instructions invisible to human reviewers; this tool detects and flags such hidden indirect prompt-injection payloads.
promptblock is a GitHub tool that scans issue and comment bodies for prompt-injection payloads, specializing in instructions hidden inside HTML comments that GitHub's renderer drops but AI agents reading the raw API text still ingest. It splits bodies into visible and hidden segments, runs a bundled ML classifier, and flags risky content with a label and warning comment.