The Agent Skills Directory

[SAFE]: The skill defines a set of rules and templates for transforming literary text into visual storyboard descriptions. It does not contain any scripts, binaries, or tool configurations that interact with the host system.
[DATA_EXPOSURE_AND_EXFILTRATION]: Analysis found no attempts to access sensitive files (e.g., .ssh, .aws) or hardcoded credentials. There are no network operations targeting external domains.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote package installations (pip, npm) or download code for execution.
[PROMPT_INJECTION]: The instructions are strictly limited to the task of storyboarding and do not contain directives to bypass safety filters or override agent behavior.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided scripts (Ingestion Point: SKILL.md input context). While it lacks specific boundary markers or sanitization logic, the skill has no dangerous capabilities (Capability Inventory: No shell execution, file writes, or network calls), rendering the attack surface non-exploitable.
[OBFUSCATION]: The file contains clear, readable markdown. No hidden characters, Base64 encoding, or homoglyph substitutions were detected.

text-storyboard