The Agent Skills Directory

[SAFE]: The skill provides marketing strategies and growth ideas for SaaS products. No security risks, such as data exfiltration or malicious commands, were detected.
[PROMPT_INJECTION]: The skill ingests untrusted data from a marketing context file. Ingestion points: .agents/product-marketing-context.md. Boundary markers: Absent. Capability inventory: No execution capabilities detected. Sanitization: Absent. This creates a minor surface for indirect prompt injection, but the risk is negligible due to the lack of dangerous tools or operations.
[DATA_EXFILTRATION]: The skill reads from a local context file .agents/product-marketing-context.md to provide relevant advice. This is standard behavior and does not involve exfiltrating data to external sources.

marketing-ideas