Lucene search
+L

33 matches found

EUVD
EUVD
•added 2026/09/15 3:18 p.m.•19 views

EUVD-2026-78658

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimatebatchcost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parallel...

7.1CVSS5.8AI score0.00476EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/09/15 12:00 a.m.•45 views

PT-2026-92103

atomic-agents-stack before 1.1.0 contains a path traversal vulnerability in the dashboard HTTP server that allows remote attackers to read arbitrary files by supplying directory traversal sequences in request paths. Attackers can bypass path containment checks by including '../' segments in...

8.7CVSS6.1AI score0.01332EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/15 12:00 a.m.•9 views

CVE-2026-91989: Improper Limitation of a Pathname to a Restricted Directory

atomic-agents-stack before 1.1.0 contains a path traversal vulnerability in the dashboard HTTP server that allows remote attackers to read arbitrary files by supplying directory traversal sequences in request paths. Attackers can bypass path containment checks by including '../' segments in...

8.7CVSS6.1AI score0.01332EPSS
SaveExploits0References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/15 12:00 a.m.•14 views

CVE-2026-91987: Allocation of Resources Without Limits or Throttling

atomic-agents-stack before 1.1.0 contains a cost-guardrail bypass in the estimatebatchcost function that returns zero cost for unknown models not in the pricing table. Attackers can configure deployments with unknown model identifiers to bypass daily cost caps and exceed budget limits in parallel...

7.1CVSS5.8AI score0.00476EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/09/15 12:00 a.m.•21 views

PT-2026-92102

atomic-agents-stack before 1.1.0 accepts cleartext HTTP schemes in the HTTP MCP server-registry backend factory, allowing network man-in-the-middle attackers to rewrite catalog responses. Attackers can inject arbitrary command and argument values that are spawned as local subprocesses by...

9.2CVSS6.4AI score0.00318EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/15 12:00 a.m.•11 views

CVE-2026-91988: Cleartext Transmission of Sensitive Information

atomic-agents-stack before 1.1.0 accepts cleartext HTTP schemes in the HTTP MCP server-registry backend factory, allowing network man-in-the-middle attackers to rewrite catalog responses. Attackers can inject arbitrary command and argument values that are spawned as local subprocesses by...

9.2CVSS6.4AI score0.00318EPSS
SaveExploits0References2
osv_ghsa
osv_ghsa
•added 2026/08/17 9:50 p.m.•22 views

GHSA-J659-8XH6-5PQ5 atomic-agents-stack: Parallel helper/delegate batch reserves $0 for models absent from the pricing table, bypassing the cost-cap fan-out guard

estimatebatchcost atomicagents/agent.py looks up the per-model output price with PRICING.getmodel, , returning 0.0 for any model not in the hardcoded pricing table. checkbatchreservation then early-returns when the reservation is 0 and that an over-cap unknown-model batch raises...

8.7CVSS5.7AI score0.00476EPSS
SaveExploits0References3
Snyk
Snyk
•added 2026/08/17 9:50 p.m.•10 views

Allocation of Resources Without Limits or Throttling

Overview atomic-agents-stack is a Spec + reference implementation for vault-native, multi-runtime AI agents Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling due to improper handling of unknown models in the PRICING lookup within the...

8.7CVSS5.8AI score
SaveExploits0References2
Github Security Blog
Github Security Blog
•added 2026/08/17 9:49 p.m.•25 views

atomic-agents-stack: HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE)

The HTTP MCP server-registry backend factory atomicagents/mcpregistry/http.py, makehttpmcpserverregistrybackendfromurl accepts both http and https schemes. Catalog entries carry command/args that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by...

6.2AI score
SaveExploits0References3Affected Software1
osv_ghsa
osv_ghsa
•added 2026/08/17 9:49 p.m.•22 views

GHSA-XHCR-CQFR-M3HV atomic-agents-stack: HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE)

The HTTP MCP server-registry backend factory atomicagents/mcpregistry/http.py, makehttpmcpserverregistrybackendfromurl accepts both http and https schemes. Catalog entries carry command/args that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by...

8.7CVSS6.3AI score0.00318EPSS
SaveExploits0References3
Snyk
Snyk
•added 2026/08/17 9:49 p.m.•9 views

Resources Downloaded over Insecure Protocol

Overview atomic-agents-stack is a Spec + reference implementation for vault-native, multi-runtime AI agents Affected versions of this package are vulnerable to Resources Downloaded over Insecure Protocol via the makehttpmcpserverregistrybackendfromurl process. An attacker can execute arbitrary...

8.7CVSS6.1AI score
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/08/17 12:00 a.m.•40 views

PT-2026-92101

Name of the Vulnerable Software and Affected Versions atomic-agents-stack versions prior to 1.1.0 Description A cost-guardrail bypass exists in the estimate batch cost function within atomic agents/agent.py. The function uses PRICING.getmodel, to look up per-model output prices, which returns a...

7.1CVSS5.6AI score0.00476EPSS
SaveExploits0References9
Snyk
Snyk
•added 2026/08/13 2:17 p.m.•8 views

Directory Traversal

Overview atomic-agents-stack is a Spec + reference implementation for vault-native, multi-runtime AI agents Affected versions of this package are vulnerable to Directory Traversal via the DashboardHandler.doGET process in the dashboard HTTP server, which constructs filesystem paths from...

8.2CVSS6AI score
SaveExploits0References2
Rows per page
Query Builder