Skip to content
fr Sign in
6.0 Medium

CVE-2026-71492 Banks generates meaningful LLM prompts using a simple template language

Description

Banks generates meaningful LLM prompts using a simple template language. Prior to version 2.4.5, DirectoryPromptRegistry.set() in src/banks/registries/directory.py interpolates attacker-controlled Prompt.name and Prompt.version values into a Path without canonicalization or containment validation. Relative traversal such as ../victim/foo and an absolute Prompt.name can escape or discard the configured registry root, while overwrite=True permits replacement of existing target files. The poisoned name is persisted in index.json and reconstructed by _load(), allowing the out-of-root path to survive later registry loads. An application that forwards request data into these fields can therefore write Prompt.raw bytes to attacker-chosen paths writable by the application process. This issue is fixed in version 2.4.5.

Affected products and versions

Product Affected versions Fixed in
banks 2.4 earliest → < 2.4.5 2.4.5

References

Timeline

  1. Published
  2. Last modified

Other CVEs of banks

The 6 CVEs of banks →
CVE-2026-107717 Banks generates meaningful LLM prompts using a simple template language 6.5 Medium CVE-2026-107716 Banks generates meaningful LLM prompts using a simple template language 7.3 High CVE-2026-61536 Banks generates meaningful LLM prompts using a simple template language 7.5 High CVE-2026-62663 Banks generates meaningful LLM prompts using a simple template language 7.5 High
Track this CVE