perf-profile
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted codebase data during its profiling phases, which represents a potential surface for indirect prompt injection.
- Ingestion points: Codebase analysis instructions in Phase 3 targeting CPU, memory, and rendering functions.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the analyzed code are present.
- Capability inventory: The skill is configured to use the Read, Glob, Grep, and Bash tools.
- Sanitization: No sanitization, escaping, or filtering of the ingested codebase content is performed before processing.
Audit Metadata