The Agent Skills Directory

[SAFE]: The skill's primary functions involve analyzing local source code and design assets to ensure compliance with Apple's HIG. All operations described are consistent with its stated purpose of improving UI/UX design.
[COMMAND_EXECUTION]: The skill utilizes local CLI commands such as /erne-hig and /erne-quality-gate. These appear to be internal project tools used for scanning source files, analyzing videos, and generating design tokens. There is no evidence of these commands being used for malicious purposes or accessing sensitive system areas.
[DATA_EXPOSURE]: While the skill reads project files (e.g., ./src/screens/, ./reference.mp4), it does so within the context of a design audit. There are no network operations or exfiltration patterns detected that would suggest sensitive data is being sent to external servers.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (source code and video files). While this presents a surface for indirect injection, the risk is mitigated by the specific design-focused tasks it performs, and no exploitable capability chains were identified.

hig