The Agent Skills Directory

[SAFE]: The skill provides structured guidance and templates for marketing content. No malicious patterns such as command execution, data exfiltration, or obfuscation were found.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted data from marketing context files and user prompts. • Ingestion points: .agents/product-marketing-context.md and user-provided competitor research. • Boundary markers: No specific delimiters or security instructions are used to isolate ingested data. • Capability inventory: Limited to content generation and formatting within the agent context. • Sanitization: No explicit data validation or sanitization is performed.

competitor-alternatives