The Agent Skills Directory

[SAFE]: The skill provides purely instructional content and strategic frameworks for mobile app retention. It does not include any scripts, executable code, or system commands.
[INDIRECT_PROMPT_INJECTION]: The skill suggests reading an external file (app-marketing-context.md) for context. While this file represents a potential ingestion point for untrusted data, the skill lacks the capabilities (such as network access, file writing, or command execution) required to weaponize an injection attack. The risk is considered negligible.
[DATA_EXFILTRATION]: There are no network operations, API calls, or commands that could exfiltrate data from the user's environment.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or instructions to handle sensitive credentials in an unsafe manner were found.
[OBFUSCATION]: The content is written in clear, standard Markdown with no hidden characters, encoded strings, or homoglyph attacks.

retention-optimization