The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and configuration files aimed at marketing and content strategy. There is no executable code, script automation, or remote resource fetching.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read .agents/marketing-context.md as a source of truth. While this represents a data ingestion surface for indirect prompt injection, the skill lacks any high-risk capabilities—such as file writing, network operations, or command execution—that could be exploited by malicious content within that file. The risk is minimal as the agent's role is restricted to strategy and brief generation.
[CREDENTIALS_SAFE]: No hardcoded secrets, API keys, or sensitive environment variable patterns were detected in the instructions or metadata.

content-engine