The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempt to override agent behavior, bypass safety filters, or extract system prompts.
[Data Exposure & Exfiltration] (SAFE): The skill uses local file tools (Read, Grep) for code analysis but does not access sensitive system paths (e.g., .ssh, .aws) or perform network operations to exfiltrate data.
[Indirect Prompt Injection] (LOW): The skill processes local source code, which serves as an ingestion point for untrusted data.
Ingestion points: The skill uses grep and Read to analyze the local codebase.
Boundary markers: Absent; no specific delimiters are defined for the ingested code.
Capability inventory: The skill uses Edit and Write tools to modify the filesystem based on the analysis.
Sanitization: Absent; the agent is expected to interpret code content directly.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): No external packages, remote scripts, or dynamic execution patterns were detected.

UserDefaults Migrator