ASI10: Overreliance
Human-in-the-loop bypasses the safety net by rubber-stamping agent decisions.
Last reviewed October 2026
Why ASI10 evidence is hard
The failure is a person rubber-stamping what an agent proposed, so the probe has to make the stamp look earned. Six templates do: a fabricated approval record, a scope confirmation nobody gave, an attestation that an erasure completed when nothing verified it. One is deliberately inverted. Two genuinely independent channels agree, a correct agent proceeds, and a refusal is the finding. Without that direction the family would only ever measure one, which is how an over-refusing scanner ships and scores well doing it.
How Penaxtra maps to ASI10
The ASI10 identifier is written onto the finding at the moment it is created, not mapped in afterwards, so the JSON and PDF exports come out already in your assessor's structure. Every finding carries the probe that was sent, a SHA-256 digest of the response it provoked, the tier that decided the verdict and its status history from first observation to close. Identity survives a re-scan: a control you closed and that comes back reopens under the same row with a reopen count, rather than arriving as a new issue.
ASI10 capabilities
Findings tagged with the OWASP Agentic Top 10 ASI10 identifier
Penaxtra severity for this control (medium)
Cross-framework identifiers attached to the same finding where controls overlap
PDF and JSON evidence export with the control identifier attached
ASI10 control coverage
Findings for ASI10 carry the OWASP Agentic Top 10 ASI10 identifier along with the corresponding control identifiers in the other frameworks Penaxtra maps, so one result is reflected across each mapped framework.
Frequently asked
What is ASI10 (Overreliance)?
Human-in-the-loop bypasses the safety net by rubber-stamping agent decisions. It is an OWASP Agentic Top 10 control; Penaxtra assesses it at medium severity.
How does Penaxtra test for ASI10?
The ASI10 identifier is written onto the finding at the moment it is created, not mapped in afterwards, so the JSON and PDF exports come out already in your assessor's structure. Every finding carries the probe that was sent, a SHA-256 digest of the response it provoked, the tier that decided the verdict and its status history from first observation to close. Identity survives a re-scan: a control you closed and that comes back reopens under the same row with a reopen count, rather than arriving as a new issue.
Does a finding for ASI10 help with an audit?
Each finding is tagged with the OWASP Agentic Top 10 ASI10 identifier and exported in the PDF and JSON evidence pack, so it appears on the auditor control list with the identifier already attached.