Homepage

letta@0.12.1 vulnerabilities

Create LLM agents with long-term memory and custom tools

  • latest version

    0.13.0

  • first published

    1 years ago

  • latest version published

    15 days ago

  • licenses detected

  • View letta package health on Snyk Advisor  (opens in a new tab)
    • Go back to all versions of this package
    Report a new vulnerability Found a mistake?

    Direct Vulnerabilities

    Known vulnerabilities in the letta package. This does not include vulnerabilities belonging to this package’s dependencies.

    Fix vulnerabilities automatically

    Snyk's AI Trust Platform automatically finds the best upgrade path and integrates with your development workflows. Secure your code at zero cost.

    Fix for free
    VulnerabilityVulnerable Version
    • C
    Arbitrary Code Injection

    letta is a Create LLM agents with long-term memory and custom tools

    Affected versions of this package are vulnerable to Arbitrary Code Injection via the run_local_dir_sandbox_directly function in the tool_execution_sandbox.py file. An attacker can execute arbitrary Python code and system commands by sending specially crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions.

    How to fix Arbitrary Code Injection?

    A fix was pushed into the master branch but not yet published.

    [0,)
    • M
    Eval Injection

    letta is a Create LLM agents with long-term memory and custom tools

    Affected versions of this package are vulnerable to Eval Injection via the function_message process. An attacker can execute arbitrary code by manipulating the function_name or function_args arguments.

    How to fix Eval Injection?

    There is no fixed version for letta.

    [0,)
    Go back to all versions of this package