performance-profiling
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a collection of reference documents for developers. It does not contain any executable code, remote script downloads, or instructions that attempt to override AI safety constraints. All external links point to official Apple developer documentation, which is a trusted and well-known source.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of external project files, which serves as an ingestion point for untrusted data. While no malicious instructions are present in the skill itself, the agent's interaction with user-provided code creates a surface for indirect prompt injection. Ingestion points: Project source code and logs read via the Read and Grep tools. Boundary markers: Absent. Capability inventory: Bash, Read, Glob, Grep. Sanitization: Absent.
Audit Metadata