The Agent Skills Directory

[PROMPT_INJECTION]: No evidence of prompt injection or bypass techniques found. The instructions are focused entirely on the domain-specific task of scriptwriting and project state management.
[DATA_EXFILTRATION]: No network operations or external data exfiltration patterns were detected. The skill operates within a defined local project directory structure.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found in the skill or its reference files.
[COMMAND_EXECUTION]: The skill does not contain any shell command execution or subprocess spawning. It focuses on text generation and markdown file management.
[EXTERNAL_DOWNLOADS]: No external downloads or remote script executions are present. All references are to local markdown files provided within the skill package.
[OBFUSCATION]: No obfuscated strings, Base64 encoding, or hidden characters were detected in the source text or metadata.
[DYNAMIC_EXECUTION]: The skill does not utilize any dynamic code generation or runtime execution patterns.
[SAFE_PRACTICES]: The skill demonstrates good security posture by including a dedicated 'compliance-checklist.md' and a '/compliance' command to help the AI detect and mitigate risky content during the creative process.

short-drama