axiom-audit-memory
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on static and diagnostic analysis of Swift source code to identify memory management issues. All search patterns and reasoning steps are aligned with the stated purpose and involve standard developer tools.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection because it processes external data (Swift source code and crash reports) using the agent's reasoning capabilities.
- Ingestion points: The skill reads local Swift files using Glob, Grep, and Read tools, and processes crash artifacts like .ips and .crash files.
- Boundary markers: No specific delimiters or safety instructions are provided to separate user-provided code from agent instructions.
- Capability inventory: The agent has the ability to read files, search project contents, and execute the xcsym command line tool.
- Sanitization: No sanitization or validation of the ingested code content is performed before processing.
Audit Metadata