prompt-injection-detector
Prompt injection vulnerability scanner: statically detects LLM API call sites, traces untrusted data flowing into system prompts and user messages, and classifies injection countermeasures (none/weak/adequate). Read-only. Trigger: /prompt-inspect
Pinned to revision 345dfaa59547, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/prompt-injection-detector/SKILL.md
- skills/prompt-injection-detector/README.md
- skills/prompt-injection-detector/scripts/prompt-scan.ps1
Every link opens the file at its source, pinned to the revision this page describes.