code-quality
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Command Execution] (SAFE): The skill invokes ruff, mypy (via uv run), and pytest to analyze local source code. These are standard operations for the stated purpose of the skill and do not pose a security risk in this context.
- [Indirect Prompt Injection] (SAFE): The skill ingests untrusted data from the repository's source files and passes it to the code-simplifier sub-agent. This is an indirect prompt injection surface, but it is considered safe in this context. Evidence Chain: 1. Ingestion points: Local .py files in synapse/ and tests/. 2. Boundary markers: Absent in the task prompt. 3. Capability inventory: Execution of linting/testing tools and sub-agent delegation. 4. Sanitization: Absent.
Audit Metadata