vetkit.llm-app.llm-output-file-path
A file path chosen by a language model is used to write or delete files. A prompt-injected response can point it outside the intended directory (../, absolute paths) and overwrite source code, shell profiles or credentials.
Last updated:
Suite: AI code risks
javascript, typescript
A file path chosen by a language model is used to write or delete files. A prompt-injected response can point it outside the intended directory (../, absolute paths) and overwrite source code, shell profiles or credentials.
Category: LLM SECURITY · Engine rule severity: WARNING
How to fix it
Resolve the model-supplied path against a fixed workspace directory, reject it unless the resolved path stays inside that directory (and is not a symlink out of it), or let the model choose only a file name and apply path.basename to it.
References
Source: packages/engine/rules/llm-app/javascript.yml.
python
A file path chosen by a language model is used to write or delete files. A prompt-injected response can point it outside the intended directory (../, absolute paths) and overwrite source code, shell profiles or credentials.
Category: LLM SECURITY · Engine rule severity: WARNING
How to fix it
Resolve the model-supplied path against a fixed workspace directory and reject it unless the resolved path stays inside that directory (Path.resolve().is_relative_to), or let the model choose only a file name and apply os.path.basename to it.
References
Source: packages/engine/rules/llm-app/python.yml.
Generated from shipped rule definitions at build time. Matching is a review signal, not proof of exploitability. “generic” denotes text matching, not complete language or framework coverage. Runtime configuration and available tools affect whether a rule runs.