The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the skill instructions or referenced files.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its data ingestion model. * Ingestion points: Instructions in SKILL.md prompt the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md. * Boundary markers: None identified. * Capability inventory: No dangerous tools or functions (such as subprocess calls, file-write operations, or network exfiltration) were found across any file in the skill. * Sanitization: No validation or sanitization is performed on the ingested content.

lead-magnets