The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute several command-line profiling tools, including cProfile, kernprof, memory_profiler, and py-spy to analyze Python script performance.
[PRIVILEGE_ESCALATION]: The instructions include usage examples of the sudo command in conjunction with py-spy. This is a standard requirement for sampling profilers to attach to running processes but represents an escalation of privileges.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze Python code provided by users, which serves as an ingestion point for untrusted data. A malicious user could potentially embed instructions within the code snippets being optimized.
Ingestion points: User-provided Python code processed by the agent (referenced in SKILL.md).
Boundary markers: Absent; there are no specific delimiters or warnings to ignore embedded instructions in the analyzed code.
Capability inventory: Shell command execution via profiling tools in SKILL.md and references/optimization-patterns.md.
Sanitization: Absent; the skill does not specify methods for sanitizing or escaping the user-provided code before analysis.

python-performance-optimization