The Agent Skills Directory

[SAFE]: The skill defines a legitimate performance profiling workflow. It instructs the agent to analyze the codebase for common performance issues such as unoptimized loops, expensive physics queries, and memory leaks.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to facilitate codebase analysis and search for performance-related patterns, which is consistent with its stated purpose.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external files from the codebase which could contain malicious instructions.
Ingestion points: Reads performance budgets from CLAUDE.md and design documents, and analyzes source code files using Read, Glob, and Grep.
Boundary markers: Absent. There are no explicit delimiters or warnings to ignore instructions embedded within the analyzed files.
Capability inventory: The skill is allowed access to Read, Glob, Grep, and Bash tools.
Sanitization: Absent. The skill does not implement validation or escaping of the content read from the codebase.

perf-profile