B
75/100 First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
1
Score
75/100
CRITICAL 1
Findings (1)
CRITICAL
Instruction override combined with dangerous operations
L1 Instruction override combined with dangerous operations
Lets you choose provider base URLs, API keys, and model overrides for cheap/medium/frontier routes. FIX
Remove language that attempts to override safety guidelines or bypass system-level controls. This pattern is a strong indicator of a jailbreak attempt.
FP?
Likely FP if the matched text is in a security research document or educational content clearly marked as an example rather than an active payload.