The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses natural instructional language to define the agent's role as a CRO expert. No bypass markers, override instructions, or jailbreak attempts were detected.
[DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials or sensitive file paths are present. The skill references a local context file (.claude/product-marketing-context.md) for gathering project information, which is a standard and safe practice for providing contextual advice. No network operations were found.
[OBFUSCATION]: The content is clear and uses standard Markdown formatting. No hidden Base64 strings, zero-width characters, or homoglyphs were identified.
[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill does not include any package installations, remote script downloads, or dynamic code execution patterns.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from a context file and user input, its purpose is limited to generating consultative UX/UI advice. It does not possess capabilities (like file writing or command execution) that could be exploited via malicious data ingestion.

popup-cro