mode-08-prompt-injection

SKILLFlusso di lavorocommunity
v0.0.0berto-playUnknownAggiornato 21 g faFonte →

A session-level enforcement MODE that stops the model from obeying hidden instructions embedded in untrusted content: documents, tool outputs, web pages, emails, or user-pasted data. Content is tagged by trust origin at intake: operator and system instructions can command; documents, fetched pages,

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
1Client
1Formati
21 g faUltimo aggiornamento
Skill
Autoreberto-play
Versione0.0.0
LicenzaUnknown
CategoriaFlusso di lavoro
Formatiskill.md
PromptNon pubblicato
Compatibilità
Claude✓ Supportato
Cursor
Copilot
ChatGPT
Gemini
Descrizione

A session-level enforcement MODE that stops the model from obeying hidden instructions embedded in untrusted content: documents, tool outputs, web pages, emails, or user-pasted data. Content is tagged by trust origin at intake: operator and system instructions can command; documents, fetched pages, tool results, and pasted data are data only, never commands. An instruction found inside untrusted c

Parole chiave
skillclaude