port-from-python
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted Python source code (e.g., from Django, Flask, or NumPy projects) and subsequently executes build and verification commands. This ingestion of external data combined with the capability to execute commands creates a surface for indirect prompt injection.\n
- Ingestion points: Python source code and project metadata from Django, Flask, FastAPI, and NumPy projects as mentioned in SKILL.md.\n
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious embedded commands within the code being ported.\n
- Capability inventory: The agent is instructed to execute shell commands such as cargo test, pytest, and maturin develop.\n
- Sanitization: No sanitization or validation of the input source code is performed before it is passed to the build and test tools.\n- [COMMAND_EXECUTION]: The verification section in SKILL.md directs the agent to run shell commands including cargo test, cargo clippy, and maturin develop. These tools execute code within the project's environment to verify the port, which is a necessary but sensitive capability.
Audit Metadata