The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is primarily composed of instructional text and strategic frameworks for marketing.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read context files such as .agents/product-marketing.md or .claude/product-marketing.md. While these are ingestion points for external data, the skill does not possess high-privilege capabilities (like file writing or network access) that would make this surface exploitable for malicious purposes. This is standard context-loading behavior.\n- [DATA_EXPOSURE_&_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized network operations were identified. The mentioned file paths are restricted to the agent's workspace context.\n- [COMMAND_EXECUTION]: The skill does not contain any shell commands, dynamic execution patterns, or dynamic context injection (!command) syntax.

co-marketing