The Agent Skills Directory

[DATA_EXPOSURE_AND_EXFILTRATION]: The skill generates image URLs for the public memegen.link service. This is a well-known public API, and no sensitive local data (such as credentials, environment variables, or SSH keys) is accessed or transmitted.
[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The helper script scripts/meme_generator.py relies exclusively on Python standard libraries (urllib.parse and argparse). It does not download external packages or execute remote code via shell pipes.
[PROMPT_INJECTION]: The instructions in SKILL.md and README.md are focused on the intended functionality of generating memes and do not contain patterns designed to override agent safety constraints or extract system prompts.
[DYNAMIC_EXECUTION]: The Python script is used for string formatting and URL construction. No unsafe use of eval(), exec(), or dynamic loading of untrusted modules was found.
[OBFUSCATION]: All content, including URLs and the Python script logic, is in plain text with no use of Base64, zero-width characters, or homoglyphs.

meme-factory