AI agent skills pass every scanner. 87% still degrade agent safety

4 comments

• skillsandwills 6 hours ago ago

  have been looking into a skill repo that is "safe". If I want to drop one of these hardened skills into production, what's the failure mode? are you also exploring if the default guardrails ever block " legitimate" workflows?

  [-]
  • shadab_nazar 6 hours ago ago

    [dead]

• raffaeleg an hour ago ago

  [dead]

• shadab_nazar 6 hours ago ago

  [dead]