convention-python
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill directs the agent to automatically modify Python files during read/write operations. This creates an indirect prompt injection surface where the agent could be influenced by instructions embedded in the code it is correcting.\n
- Ingestion points: Reads the content of
.pyfiles to check for convention compliance as described in the automatic correction section of SKILL.md.\n - Boundary markers: The skill lacks instructions to isolate code content or to explicitly ignore any linguistic instructions found within strings or comments in the code.\n
- Capability inventory: The skill requires file-writing capabilities to perform the automatic fixes (renaming, adding type hints, rewriting docstrings) mentioned throughout the document.\n
- Sanitization: There are no safety checks or sanitization steps defined to ensure the agent does not treat code comments or string literals as directives.\n- [NO_CODE]: This skill consists of a single markdown file containing only instructions and code examples. It does not include or reference any external scripts, binaries, or packages.
Audit Metadata