The Agent Skills Directory

[SAFE]: The skill is entirely composed of informational markdown files and does not contain any executable scripts, binaries, or dynamic code execution patterns.
[NO_CODE]: No source code (Python, JavaScript, etc.) or configuration files for automated tools are present in the skill package.
[PROMPT_INJECTION]: The skill identifies potential ingestion points for untrusted data by instructing the agent to read marketing context from files like .agents/product-marketing.md. However, since the skill defines no dangerous capabilities, the risk associated with this surface is negligible.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (as mentioned in SKILL.md).
Boundary markers: No specific delimiters or safety instructions are provided for these context files.
Capability inventory: No tool use, subprocess execution, or write permissions are requested or utilized by the skill.
Sanitization: No sanitization or validation logic is present for the ingested context data.
[SAFE]: No hardcoded credentials, sensitive file access (e.g., SSH keys, AWS configs), or exfiltration patterns were detected in any of the reference documents.

offers