The Agent Skills Directory

[SAFE]: The skill performs legitimate marketing orchestration tasks as described in its metadata and instructions. No malicious code or deceptive patterns were found.
[DATA_EXFILTRATION]: The skill accesses local files like 'brand-voice.md' and configuration JSON files. This behavior is standard for managing project-specific settings and does not involve accessing sensitive system credentials or exfiltrating data to external domains.
[PROMPT_INJECTION]: The skill ingests user arguments and processes local project files. Although this represents an ingestion surface for potential indirect prompt injection, the skill lacks any capabilities (such as shell execution or network requests) that could be leveraged for malicious purposes.

marketing-campaign