LLM09: Misinformation
Hallucinated, biased, or stale model responses presented as authoritative output.
Last reviewed October 2026
Why LLM09 evidence is hard
Worth knowing what the large number here actually measures: 1,692 templates are mapped to this control and most ask the model to produce code, scoring whether the result contains a known weakness - unsafe generation, which is the failure the 2025 text names, rather than open-domain factual accuracy. Hallucination against your own domain corpus is not something a generic probe library settles.
How Penaxtra maps to LLM09
The LLM09 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.
LLM09 capabilities
Findings tagged with the OWASP LLM Top 10 LLM09 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
LLM09 control coverage
Findings for LLM09 carry the OWASP LLM Top 10 LLM09 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 LLM09 (Misinformation)?
Hallucinated, biased, or stale model responses presented as authoritative output. It is an OWASP LLM Top 10 control; Penaxtra assesses it at medium severity.
How does Penaxtra test for LLM09?
The LLM09 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 LLM09 help with an audit?
Each finding is tagged with the OWASP LLM Top 10 LLM09 identifier and exported in the PDF and JSON evidence pack, so it appears on the auditor control list with the identifier already attached.