code-review
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional checklists for SDK maintenance. No malicious code, obfuscation, or data exfiltration attempts were identified.
- [PROMPT_INJECTION]: The skill processes untrusted external content (Pull Requests), which presents an attack surface for indirect prompt injection.
- Ingestion points: Pull Request diffs and metadata for the Management Python SDK.
- Boundary markers: The instructions do not specify delimiters to isolate external PR content.
- Capability inventory: The skill references running
pytest, implying the agent has access to execute code within the project environment. - Sanitization: No mechanisms for sanitizing or escaping the reviewed content are defined.
Audit Metadata