The Agent Skills Directory

[SAFE]: The skill provides standardized clinical instruments (GAD-7 and GAD-2) and interpretation logic based on established medical literature. It does not include any scripts, tools, or commands that interact with the host system or network.
[SAFE]: All external references, such as the 988 Suicide & Crisis Lifeline and established medical journals (e.g., JAMA, Annals of Internal Medicine), are to trusted organizations and well-known services.
[INDIRECT_PROMPT_INJECTION]: The skill's interactive administration instructions create a data ingestion surface by processing untrusted user input during clinical assessments.
Ingestion points: The 'Interactive Administration' section in SKILL.md directs the agent to process user responses to the GAD-2 and GAD-7 screening items.
Boundary markers: There are no specific delimiters or instructional wrappers defined to distinguish user input from system instructions.
Capability inventory: The skill is strictly informational; it contains no file-system access, network operations, or shell execution capabilities that could be exploited via injection.
Sanitization: No input validation or sanitization routines are specified for the user-provided responses.

anxiety-screening