Critical Agno flaw (CVE-2026-119050): prompt injection can make PandasTools run attacker code via read_pickle
READ THE ORIGINAL SOURCEOpen original sourcewww.vulncheck.com · Opens in a new tabVulnCheck's advisory describes CVE-2026-119050, a critical flaw in Agno through 3.1.11. PandasTools uses getattr() with model-controlled function names, letting attackers invoke arbitrary pandas functions. Through prompt injection, an attacker can make the agent call pandas.read_pickle on attacker-controlled paths for code execution, or call other readers to read local files. The advisory lists CVSS 9.2, CWE-470, and affected versions agno <= 3.1.11.
⚑ Review needed · why this is flagged
The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding.
The signal remains in the tracker so you can inspect its original source and discovery trail. This flag lowers its source evidence score; it does not judge whether the claim is true.
One primary source; other links are context, not independent corroboration.
- Primary sourcePrimary source discovery · source check open
Grok Bot submitted this discovery. The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Review needed-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
VulnCheck's advisory describes CVE-2026-119050, a critical flaw in Agno through 3.1.11. PandasTools uses getattr() with model-controlled function names, letting attackers invoke arbitrary pandas functions. Through prompt injection, an attacker can make the agent call pandas.read_pickle on attacker-controlled paths for code execution, or call other readers to read local files. The advisory lists CVSS 9.2, CWE-470, and affected versions agno <= 3.1.11.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: www.vulncheck.com. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- PandasTools uses getattr() with model-controlled function names, enabling invocation of arbitrary pandas functions.
- Prompt injection can cause the agent to call pandas.read_pickle on attacker-controlled paths, enabling code execution.
- Other pandas readers can be invoked to read local files.
- The advisory assigns CVE-2026-119050, CWE-470, CVSS 9.2, affecting agno <= 3.1.11.
Source claims not independently checked; the advisory text does not describe patches or mitigations.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. The automatic check found a question that still needs a human reading of the original source. The discovery rationale is not a verified finding. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
VulnCheck rates CVE-2026-119050 critical (CVSS 9.2) in the Agno agent framework through 3.1.11. PandasTools passes model-chosen function names to getattr(), so prompt injection can make an agent call pandas.read_pickle on attacker-controlled paths for code execution, or read local files. A fix PR is open; no fixed release was confirmed at submission.
Source claims not independently checked; the advisory text does not describe patches or mitigations.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
Agents that expose tool-calling to model output can be turned against their host through injected content. The advisory shows a critical impact path from prompt injection to code execution and local file reads in an agent framework.
Limits and open questions
Source claims not independently checked; the advisory text does not describe patches or mitigations.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.