The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions to override agent behavior, bypass safety filters, or reveal system prompts were detected. The content consists of educational copywriting frameworks.
[Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local files, environment variables, or hardcoded secrets. There are no network operations (curl, wget, etc.) to external domains.
[Remote Code Execution] (SAFE): No package installations (pip, npm) or remote script downloads are present. The skill does not invoke any shells or subprocesses.
[Persistence & Privilege Escalation] (SAFE): There are no commands targeting system configuration files, startup scripts, or administrative privileges.
[Obfuscation] (SAFE): No Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques were identified in the text or metadata.
[Indirect Prompt Injection] (SAFE): While the skill is designed to process user-provided script topics, it does not ingest untrusted data from external URLs or APIs, and it lacks the high-risk capabilities necessary for an exploit chain.

scriptwriting-methodology