Security readout for executives and security teams
Plain-English summary
Agno agents through version 2.5.8 may execute attacker-controlled code when malicious instructions are hidden in processed web pages or documents. If vulnerable execution tools are enabled, compromise could expose data, alter systems, or interrupt services without authentication or user interaction.
Executive priority
Treat internet-facing or untrusted-content-processing deployments as an immediate priority. Quickly identify affected versions and enabled execution tools, reduce exposure, and seek confirmed vendor remediation. Prioritize credential rotation and incident review where unexpected execution is detected. Lower urgency only after confirming the vulnerable tools are absent or strongly isolated.
Technical view
PythonTools and ShellTools reportedly pass unsanitized LLM-generated arguments into exec(), runpy.run_path(), and subprocess.run(). Indirect prompt injection can therefore cross the boundary from untrusted content to Python or operating-system command execution on the Agno host. The assigned CVSS 3.1 score is 9.8 under CWE-94.
Likely exposure
Highest risk applies to Agno deployments through 2.5.8 that enable PythonTools or ShellTools and allow agents to process attacker-influenced web pages, documents, or similar content. The supplied record does not identify CPEs or clarify default configurations, deployment prevalence, or whether tool access is sandboxed.
Exploitation context
The described attack is remote, unauthenticated, low complexity, and requires no user interaction. It relies on malicious instructions reaching an agent through processed content. The supplied bundle reports no CISA KEV listing and provides no evidence of active exploitation, public exploit code, or observed campaigns.
Researcher notes
The narrative explicitly identifies Agno through 2.5.8, but the structured affected-product entry contains only “n/a” and no CPEs. No fixed version, vendor advisory, patch, or exploitation evidence is supplied. Assessment of precise exposure therefore depends on local tool configuration and data flows; mitigation recommendations beyond checking vendor guidance are risk-reduction inferences from the described execution path.
Mitigation direction
- Check current Agno vendor guidance for a confirmed fixed release or official mitigation.
- Disable PythonTools and ShellTools where agents process untrusted or attacker-influenced content.
- Restrict agent execution privileges, filesystem access, credentials, and network reach.
- Isolate affected agents from sensitive production systems until remediation is confirmed.
- Review processed content and host telemetry for signs of unexpected execution.
Validation and detection
- Inventory Agno deployments and confirm installed versions.
- Identify agents configured with PythonTools or ShellTools.
- Map whether those agents ingest public web pages, documents, or other untrusted content.
- Verify execution tools are disabled, isolated, or restricted pending vendor guidance.
- Review logs for unexpected Python execution, subprocess activity, file changes, or outbound connections.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-94: Code execution behavior lookup
Code execution and unsafe deserialization weaknesses often justify reviewing execution behavior and process telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupExecution behavior lookup
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-37003 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Critical
- CVSS
- 9.8 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H3.95.9CISA-ADPVulnerability scoring details
Base CVSS 3.1 score
9.8CriticalVector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- https://yerangamage.com/cves/detail/?slug=agno-rce-toolsCVE reference, mitre
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
CWE mapping pending import
This CVE carries a CWE mapping that will resolve to a full Glexia CWE intelligence page after the official CWE import is complete.