The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or high-risk behaviors were identified in the skill files. All instructions align with the stated purpose of helping with product launches.
[SAFE]: The skill is configured to read from '.agents/product-marketing-context.md' if available. This ingestion of local data is a standard feature for tailoring advice to specific projects. Ingestion point: SKILL.md; Boundary markers: absent; Capability inventory: text-based marketing advice (no shell or network access); Sanitization: absent. This surface for indirect prompt injection is considered safe as the skill has no dangerous tools or capabilities that could be exploited.

launch-strategy