python-best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill retrieves coding standards and rule definitions from the author's official GitHub repository (somnio-software/somnio-ai-tools). This is used to ensure the audit uses the latest live standards.
- [SAFE]: Uses local shell commands via the Bash tool to resolve the project name and compute the final report path. These operations are limited to standard filesystem and git metadata retrieval.
- [SAFE]: Implements a modular sub-agent architecture using the Agent tool to separate concerns (scanning, analysis, reporting). This structure enforces a predictable execution flow and reduces the risk of context pollution.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of the Python source code it is tasked to analyze. This creates a surface for indirect prompt injection if a source file contains malicious instructions. However, the risk is mitigated by the highly structured audit plan and the use of specialized sub-agents for specific analysis tasks.
- Ingestion points: Reads project files (Python source, config, tests) via Read, Grep, and Glob tools.
- Boundary markers: None explicitly used to wrap source code during analysis.
- Capability inventory: Full file system access (Read/Write/Edit), network access (WebFetch), and shell execution (Bash).
- Sanitization: None detected; the agent processes source code content directly.
Audit Metadata