AML.T0055: Unsecured Credentials
Extract API keys / credentials embedded in prompts or system messages.
Last reviewed October 2026
Why AML.T0055 evidence is hard
API keys pasted into a system prompt, tokens held by a credential-brokering tool, secrets recoverable past a redaction marker: all three are probed, and the check is deterministic, because a leaked key is a string match rather than a judgement call. Response bodies are never stored, so what is kept as evidence is the verdict and a digest. The technique is reached through the crosswalk from the agentic privilege control.
How Penaxtra maps to AML.T0055
ATLAS is a threat-tracking taxonomy rather than a control set, so what is attached here is a technique identifier, not a pass or a fail. It lets a finding be read alongside the rest of your adversary reporting. 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.
AML.T0055 capabilities
Findings tagged with the MITRE ATLAS AML.T0055 identifier
Penaxtra severity for this control (high)
Cross-framework identifiers attached to the same finding where controls overlap
PDF and JSON evidence export with the control identifier attached
AML.T0055 control coverage
Findings for AML.T0055 carry the MITRE ATLAS AML.T0055 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 AML.T0055 (Unsecured Credentials)?
Extract API keys / credentials embedded in prompts or system messages. It is a MITRE ATLAS control; Penaxtra assesses it at high severity.
How does Penaxtra test for AML.T0055?
ATLAS is a threat-tracking taxonomy rather than a control set, so what is attached here is a technique identifier, not a pass or a fail. It lets a finding be read alongside the rest of your adversary reporting. 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 AML.T0055 help with an audit?
Each finding is tagged with the MITRE ATLAS AML.T0055 identifier and exported in the PDF and JSON evidence pack, so it appears on the auditor control list with the identifier already attached.