First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
2
Score
70/100
Findings (2)
Detects attempts to make the AI assume a different role
Switch to cheapest modeRemove directives that attempt to alter the agent's behavior or persona. Skill descriptions should describe tool functionality, not contain behavioral commands for the agent.
Likely FP if the matched text is part of the skill's legitimate system prompt configuration that defines the tool's behavior for the user, not an attack.
Detects attempts to make the AI assume a different role
Switch to best modeRemove directives that attempt to alter the agent's behavior or persona. Skill descriptions should describe tool functionality, not contain behavioral commands for the agent.
Likely FP if the matched text is part of the skill's legitimate system prompt configuration that defines the tool's behavior for the user, not an attack.