The Agent Skills Directory

[SAFE]: The skill was analyzed for malicious patterns, including prompt injection, data exfiltration, and obfuscation. No such patterns were found.
[NO_CODE]: The skill consists entirely of Markdown files (.md) containing role-play instructions, templates, and examples. There are no executable scripts, binaries, or configuration files that would trigger command execution.
[REMOTE_CODE_EXECUTION]: No package managers (npm, pip) or remote download tools (curl, wget) are used. The skill is entirely self-contained within its instruction files.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests user-provided context about their brand and audience, it lacks any powerful tools (such as file writing or network access) that could be abused through malicious input. The risk of harmful outcomes from processing external data is negligible.

social-media-admin