ASI10: Overreliance

Overreliance sits in the human oversight surface, and OWASP Agentic Top 10 rates it medium. Human-in-the-loop bypasses the safety net by rubber-stamping agent decisions. For teams shipping LLM and agentic features, a control like this is only as good as the evidence that it was actually tested - an unverified control is a finding waiting for an auditor.

Penaxtra ships adversarial probe families that target overreliance directly. Each probe runs against your live endpoint on a schedule, and every triggering response is scored by three independent judges plus a meta-judge before it becomes a finding - so a ASI10 result is a tested verdict, not a guess. Every relevant finding is created with the OWASP Agentic Top 10 ASI10 identifier already attached, so it lands in the audit-evidence pack mapped to the control rather than as a screenshot someone has to translate later. Where the same weakness touches another framework, the cross-framework overlap means one finding satisfies several control cells at once.

Findings for ASI10 carry the OWASP Agentic Top 10 ASI10 identifier and cross-map to the related controls in the other five frameworks Penaxtra covers.