The Agent Skills Directory

[SAFE]: The skill is purely informational, providing guidance on marketing strategy and engineering-as-marketing principles. It does not contain any executable scripts or automation logic.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read project-specific context files, which creates an ingestion surface for potential indirect prompt injection if those files are attacker-controlled.
Ingestion points: The skill reads data from .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md to provide tailored advice.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the contents of these context files as untrusted data or to ignore embedded instructions.
Capability inventory: The skill's capabilities are limited to providing textual advice and strategic evaluation. It contains no subprocess calls, network request tools, or file-writing logic across any of its files.
Sanitization: There is no evidence of filtering or escaping logic applied to the data ingested from the external context files.

free-tools