The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses thematic language common in creative industries (e.g., 'Simplicity as Violence', 'Kill Your Darlings'). No attempts to override safety filters, bypass instructions, or extract system prompts were detected. The instructions are focused on adherence to the creative process.
[DATA_EXPOSURE]: There are no references to sensitive file paths, environment variables, or hardcoded credentials. The skill does not perform any network operations to external domains.
[REMOTE_CODE_EXECUTION]: The skill does not contain instructions to download or execute external scripts, binary files, or packages. All logic is contained within the markdown files.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or system-level operations were found in the instructions or reference materials.
[OBFUSCATION]: All files are written in clear, human-readable markdown. No Base64, zero-width characters, or hidden Unicode tags were detected.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided briefs (Phase 1). While it lacks explicit boundary markers for this untrusted data, it possesses no dangerous capabilities (like file writing or network access) that could be exploited via an indirect injection attack.

creative-director