The Agent Skills Directory

[SAFE]: The skill provides marketing strategy recommendations based on a static list of ideas and does not possess any dangerous capabilities like network access, shell command execution, or file system modifications.
[DATA_EXPOSURE]: The skill is instructed to read local project-specific marketing context from files like .agents/product-marketing.md to customize its advice. This is an intended behavior for context-aware agents and does not involve exfiltration.
[INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which could potentially contain malicious instructions. However, because the skill has no tools for network, execution, or persistence, the risk of a successful attack is negligible.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md.
Boundary markers: The skill does not define specific delimiters for the ingested content.
Capability inventory: None. The skill only generates text recommendations.
Sanitization: No sanitization is performed on the ingested files.

marketing-ideas