The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from the user's workspace by reading context files such as .agents/product-marketing.md or .claude/product-marketing.md. However, the skill provides marketing advice to the user and lacks any high-risk capabilities like network access, file writing, or shell execution that could be exploited via these injection surfaces.
[SAFE]: The instructions and reference files contain standard marketing guidance and design patterns for referral loops, affiliate commission structures, and viral mechanisms. No signs of obfuscation, malicious persistence, or data exfiltration were detected.

referrals