axiom-audit-grdb-performance
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a legitimate static analysis tool for Swift database code. It uses standard file system tools (Glob, Grep, Read) to identify performance bottlenecks and correctness issues without performing any malicious actions. No evidence of data exfiltration, unauthorized network access, or persistence mechanisms was found.
- [PROMPT_INJECTION]: The skill possesses an inherent surface for indirect prompt injection as its primary purpose involves reading and processing untrusted project files.
- Ingestion points: The skill ingests untrusted code from
.swiftand.entitlementsfiles across the project directory (SKILL.md). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to prevent it from obeying instructions that might be embedded within the audited source files.
- Capability inventory: The agent uses
Glob,Grep, andReadtools to access file content and is instructed to perform multi-phase reasoning based on that content. - Sanitization: The skill does not mention or implement any sanitization or escaping of the ingested code before it is interpreted by the model.
Audit Metadata