axiom-audit-spritekit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate code analysis using read-only operations including Glob, Grep, and Read. It focuses on identifying technical issues specific to SpriteKit development, such as physics bitmask errors, draw call inefficiencies, and node lifecycle mismanagement.- [INDIRECT_PROMPT_INJECTION]: As an auditing tool, the skill ingests untrusted code from the local project, which creates a surface for indirect prompt injection. This risk is inherent to the tool's primary purpose.
- Ingestion points: Processes project-specific Swift files using Glob, Grep, and Read tools identified in the Phase 1 and Phase 2 search patterns.
- Boundary markers: The instructions do not define specific delimiters to separate the audited code from the agent's instructions, though the task is strictly scoped to SpriteKit pattern detection.
- Capability inventory: The skill is restricted to file reading and pattern matching. No file system write, network exfiltration, or administrative capabilities are requested or utilized.
- Sanitization: No explicit sanitization or input validation of the audited file content is performed prior to analysis.
Audit Metadata