The Agent Skills Directory

[SAFE]: The skill is composed exclusively of markdown documentation and reference materials. No code execution, persistence mechanisms, or unauthorized data access patterns were detected.
[PROMPT_INJECTION]: The skill instructs the agent to read marketing context from local files such as '.agents/product-marketing.md'. This presents a potential surface for indirect prompt injection if those files contain malicious instructions. However, the skill lacks the necessary capabilities (such as shell execution or network access) to be exploited maliciously. * Ingestion points: '.agents/product-marketing.md', '.claude/product-marketing.md', and 'product-marketing-context.md' are referenced for ingestion in SKILL.md. * Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the context ingestion prompt. * Capability inventory: The skill has no associated scripts, subprocess calls, or network operations. * Sanitization: No content validation or sanitization is performed on the ingested text.

copywriting