performance-optimization
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source code and application data to identify performance issues, which creates a standard attack surface for indirect prompt injection if that data contains malicious instructions.
- Ingestion points: Analyzes codebase architecture, data access patterns, and hot paths during the Understand and Identify phases (Phase 1 and 2).
- Boundary markers: No specific delimiters are mentioned to separate untrusted code from instructions, although the workflow includes a critical user-approval gate.
- Capability inventory: The skill possesses file-writing capabilities to apply optimizations and command-execution capabilities to run tests and profiling tools (Phase 4).
- Sanitization: There are no instructions for sanitizing or escaping the content of the analyzed files.
- [COMMAND_EXECUTION]: The workflow requires executing build, test, and profiling commands to verify optimizations in Phase 4.
- Risk Mitigation: The instructions explicitly direct the agent to ask the user how to verify if a build or profiling command is not already known, maintaining human oversight.
Audit Metadata