The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected in the skill's instructions or supporting reference files.
[DATA_EXFILTRATION]: The skill instructions recommend reading local marketing context files (e.g., .agents/product-marketing.md) to provide personalized strategy. This is a legitimate functional requirement and does not involve access to sensitive system credentials or unauthorized data transmission.
[PROMPT_INJECTION]: The skill processes untrusted content from local marketing files. While this serves as an ingestion point for potential indirect prompt injection, the skill lacks high-risk capabilities such as network access or arbitrary code execution, mitigating any associated security risk.

lead-magnets