The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill references tools such as get_flow and compare_apps to analyze external application data, which is a standard surface for indirect prompt injection. This is evaluated as safe because it is central to the skill's UX analysis purpose and lacks dangerous capabilities. 1. Ingestion points: get_flow and compare_apps tools mentioned in SKILL.md. 2. Boundary markers: None present in the instructions. 3. Capability inventory: UX design reasoning and analysis. 4. Sanitization: None defined.
[NO_CODE]: The skill consists entirely of markdown documentation and metadata, without any scripts, binaries, or executable code.
[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were found.

ryux-ux