The Agent Skills Directory

[SAFE]: The skill consists of purely instructional markdown content designed to guide an AI agent through performance code reviews. It does not contain executable scripts or binary data.
[PROMPT_INJECTION]: Analysis of the instructions confirms there are no attempts to override agent behavior, bypass safety constraints, or extract system prompts.
[DATA_EXFILTRATION]: The skill does not include any commands for accessing sensitive environment variables, credentials, or local configuration files. No network operations or external data transfer mechanisms are present.
[COMMAND_EXECUTION]: The instructions do not involve the execution of shell commands, subprocesses, or system-level operations.
[EXTERNAL_DOWNLOADS]: No external resources, remote scripts, or third-party packages are downloaded or referenced for execution.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided code (ingestion point), it lacks dangerous capabilities such as file-writing or network access that could be exploited via malicious code being reviewed. It strictly functions as a diagnostic tool.

review-performance