The Agent Skills Directory

[SAFE]: The skill consists solely of natural language instructions for an AI agent to process text. It does not contain any executable scripts, binary files, or external dependencies.
[DATA_EXFILTRATION]: No network operations (such as curl, wget, or fetch) or sensitive file access patterns were detected. Data processing is confined to the local filesystem within the designated 'docs/seo/' directory.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided blog drafts (draft.md). Although this creates a theoretical surface for indirect prompt injection, the skill has no high-privilege capabilities (like shell access or network exfiltration) to exploit, limiting the risk to the generation of incorrect or unintended text output.
[COMMAND_EXECUTION]: There are no patterns of system command execution, shell spawning, or privilege escalation. All operations involve text transformation and local file writing.

seo-social