The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown content focused on UX writing and content strategy. No patterns associated with prompt injection, data exfiltration, obfuscation, or persistence were found. The skill does not access sensitive files or perform network operations.
[NO_CODE]: The skill does not include any executable code, scripts (e.g., Python, Node.js), or shell commands. It provides natural language guidance and frameworks for text-based tasks.
[INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface as it is designed to ingest and process untrusted external data in the form of UI copy, brand guidelines, and user research. However, the skill lacks any dangerous capabilities (such as network operations, file writing, or command execution) that could be leveraged if malicious instructions were embedded in the processed text.
Ingestion points: The 'Working with this skill' section in SKILL.md encourages users to provide UI copy, research, and guidelines.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present.
Capability inventory: None. No subprocess calls, network access, or dynamic execution identified.
Sanitization: No input sanitization or validation methods are specified.

articulate