The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional text and documentation for content marketing strategy. It does not include any scripts, executable binaries, or system commands.
[DATA_EXPOSURE]: The instructions direct the agent to read local project configuration files (.claude/project-context.md and .cursor/project-context.md) to understand the project's value proposition and audience. This is a standard practice for AI agents to acquire necessary context and does not involve any external data exfiltration or credential access.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from project context files, it does so to inform marketing strategy recommendations. There are no high-risk capabilities (like file writing or shell execution) associated with this specific skill that would make this ingestion surface exploitable.

content-marketing