The Agent Skills Directory

[SAFE]: No executable code, shell commands, or network operations were found in the skill definition.
[SAFE]: The dependencies listed (foundation/marketing-os, brand-voice, etc.) are internal path references for content guidelines and do not involve external package managers or remote code downloads.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest brand and positioning data to generate posts. While this represents a data ingestion surface, the skill has no access to sensitive capabilities like file system writes, network exfiltration, or command execution, rendering the potential impact of indirect injection negligible.

linkedin-post