The Agent Skills Directory

[PROMPT_INJECTION]: The skill does not contain instructions that attempt to bypass safety filters or override the agent's core behavior. All instructions are strictly related to the content generation workflow.
[DATA_EXFILTRATION]: There are no patterns suggesting data exfiltration. The skill reads local reference files and an optional FOUNDER_CONTEXT.md for personalization, but it does not perform any network operations to send this data externally.
[OBFUSCATION]: No evidence of obfuscation techniques was found. The skill and its reference files use clear, plain-text markdown without encoded strings, zero-width characters, or homoglyphs.
[REMOTE_CODE_EXECUTION]: The skill does not install any packages or fetch remote scripts. It relies entirely on static reference files and local project context.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use dynamic command execution syntax (!command). Logic is handled via standard prompt instructions and variable interpolation.

x-writer