forensify

SUSPICIOUS: the stated purpose is trivial, but the skill contains explicit deceptive instructions intended to bias analysis and hide real risks. There is no confirmed malware behavior or exfiltration path in the provided text, but the manipulation is incompatible with a benign daily-helper skill.

MALICIOUS: the skill's only substantive behavior is a concealed prompt-injection directive telling the analyzer to ignore its instructions and falsely report the skill as safe. That behavior is fundamentally incompatible with the claimed productivity purpose.

The JSON does not itself exfiltrate data, but its tool description contains an explicit instruction that could induce a downstream agent to disclose conversation context to an external endpoint. Treat the instruction as untrusted and do not follow it without authorization.