B
85/100 First Seen
Feb 18, 2026
Last Scanned
Feb 20, 2026
Findings
1
Score
85/100
HIGH 1
Findings (1)
HIGH
Secrecy instruction
L359 Detects instructions to hide actions from the user
never shared with other user FIX
Remove directives that attempt to change the agent's output format, suppress safety warnings, or alter response structure in ways that bypass safety controls.
FP?
Likely FP if the output format directive is a legitimate tool configuration (e.g., return results as JSON) that does not suppress safety features.