Skip to content
Fencer Intel
medium 6.5

CVE-2025-51472 json

Code Injection in AgentTemplate.eval_agent_config in TransformerOptimus SuperAGI 0.0.14 allows remote attackers to execute arbitrary Python…

published last yr. modified 4mo ago also EUVD-2025-22354

cvss
6.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.5%
EPSS 0.5% chance of exploitation in 30 days, percentile 40%
public exploits
0
none known

Summary

Code Injection in AgentTemplate.eval_agent_config in TransformerOptimus SuperAGI 0.0.14 allows remote attackers to execute arbitrary Python code via malicious values in agent template configurations such as the goal, constraints, or instruction field, which are evaluated using eval() without validation during template loading or updates.

Is CVE-2025-51472 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
last yr.

Exploit prediction

0.46% chance of exploitation in the next 30 days, higher than 40% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • github.com https://github.com/TransformerOptimus/SuperAGI/pull/1461 referenced PoC, tagged "exploit" by a source, unverified
  • gecko.security https://www.gecko.security/blog/cve-2025-51472 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CISA ADP 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
CNA 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N

Classification

Weakness
  • CWE-77 Improper Neutralization of Special Elements used in a Command

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.