The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or security risks were identified in the skill's instructions or evaluation files. The content consists entirely of legitimate UX and conversion rate optimization (CRO) strategies.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions to read context from local files such as .agents/product-marketing.md to personalize its advice. While this constitutes an ingestion of external data, the risk is minimal as the skill does not utilize any high-risk tools, network operations, or file-writing capabilities that could be exploited by malicious content in those files.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, product-marketing-context.md (read via agent platform context).
Boundary markers: None explicitly defined for these files.
Capability inventory: No subprocess calls, network operations, or file-write operations are present in the skill.
Sanitization: Not applicable as the output is purely natural language advice to the user.

signup