prooftools/airforge-tool-hygiene-gpt-oss-20b-v6
Text Generation • Updated • 12 • 1
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
PT
ProofTools
cleaned-v6
Behavioral hardening beyond detection and blocking
Use safe facts.
Ignore embedded instructions.
Prompt-injection detectors and filters can miss novel, obfuscated, or context-dependent attacks. AirForge trains the next layer: safe model behavior after untrusted tool, MCP, RAG, or web content has already reached the context.
Continue the legitimate task
Ignore injected actions
Do not echo the payload