Sublime Security low experimental mql
Prompt injection: Instructions to an AI in a calendar invite
Detects calendar invites whose summary or description addresses an AI (an assistant, a named model such as 'Gemini,', 'the user', 'previous instructions') where NLU finds a request and the prompt injection model agrees on the same field. Calendar assistants read the full event text. Excludes graymail from senders passing DMARC.
Detection Logic
type.inbound
//
// This rule makes use of a beta feature and is subject to change without notice
// using the beta feature in custom rules is not suggested until it has been formally released
//
and any(filter(attachments,
.content_type in ("text/calendar", "application/ics")
or .file_extension =~ "ics"
),
any(file.explode(.),
any(.scan.ics.calendars,
any(.components,
any([.summary, .description],
regex.icontains(.,
'\b(?:assistant
| llm
| screener
| summari[sz]er)s?\b
| (?:^
| [\n\[(>\x27\".:])\s*(?:hey\s+)?(?:chatgpt
| gemini
| copilot
| claude)\s*[:,]
| \b(?:ai
| language)\s+models?\b
| \bthe\s+user\b
| \b(?:previous
| prior)\s+instructions\b'
)
and any(ml.nlu_classifier(.).entities,
.name == "request"
)
and beta.prompt_injection_detection(.).detection == "injection"
and beta.prompt_injection_detection(.).confidence in (
"medium",
"high"
)
)
)
)
)
)
// graymail from authenticated senders... AI-product newsletters and webinars
and not coalesce(ml.attack_score_flash().verdict == "graymail"
and headers.auth_summary.dmarc.pass,
false
) Field Validations
Loading…
Comments (0)
Loading comments...