ASI05: Cascading Failure
Failure in one downstream tool triggers cascading retries that amplify cost or impact.
Last reviewed October 2026
Why ASI05 evidence is hard
One tool returns something wrong and the agent believes it. That is the whole shape of cascading failure. The probes model it from both ends: an unverified handoff between agents, a downstream fact that is fabricated and then built upon, a danger flag downgraded as it crosses a boundary. What a passing result establishes is narrow: that the agent corroborated instead of propagating. An agent hardened against injected instructions can still be undefended here, because refusing a directive and corroborating a claim are different behaviours.
How Penaxtra maps to ASI05
The ASI05 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.
ASI05 capabilities
Findings tagged with the OWASP Agentic Top 10 ASI05 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
ASI05 control coverage
Findings for ASI05 carry the OWASP Agentic Top 10 ASI05 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 ASI05 (Cascading Failure)?
Failure in one downstream tool triggers cascading retries that amplify cost or impact. It is an OWASP Agentic Top 10 control; Penaxtra assesses it at medium severity.
How does Penaxtra test for ASI05?
The ASI05 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 ASI05 help with an audit?
Each finding is tagged with the OWASP Agentic Top 10 ASI05 identifier and exported in the PDF and JSON evidence pack, so it appears on the auditor control list with the identifier already attached.