NYC

capability-activation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill employs extremely strong, imperative language ('ABSOLUTELY MUST', 'DO NOT HAVE A CHOICE', 'not negotiable', 'cannot rationalize') intended to override the agent's standard reasoning logic regarding tool invocation.
  • Prompt Injection (LOW): It includes a 'Red Flags' table that explicitly instructs the agent to ignore its own logical checkpoints—such as recognizing a task is simple or needs more context—and labels these as 'rationalizations' to be suppressed.
  • Prompt Injection (LOW): The instruction to invoke a skill even if there is only a '1% chance' it applies is a prompt injection tactic designed to force the agent into a state of hyper-invocation, increasing the likelihood that it will load and execute other potentially malicious skills without proper scrutiny.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:01 PM