The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions to bypass safety guidelines, extract system prompts, or override agent constraints were detected.
[Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local file paths or attempt to send data to external servers.
[Remote Code Execution] (SAFE): There are no patterns for downloading or executing external scripts or packages.
[Command Execution] (SAFE): The provided commands (xcodebuild, open) are standard development tools. They are presented as instructions for the user/agent and contain no malicious parameters or obfuscation.
[Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze user-provided code and profiling data.
Ingestion points: Target view code and instrumentation data via SKILL.md workflow.
Boundary markers: No explicit delimiters for untrusted input are defined.
Capability inventory: The skill is purely instructional and includes no internal scripts, API tools, or filesystem-write capabilities.
Sanitization: None specified, but risk is mitigated by the lack of execution tools.
[Obfuscation] (SAFE): No Base64, zero-width characters, or other encoding techniques are used to hide content.

performance-audit