The Agent Skills Directory

[SAFE]: The skill consists entirely of documentation and evaluation test cases. It does not include any executable code, scripts, or network-enabled tools.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read external context files for product marketing information. While this creates a potential surface for indirect prompt injection, the skill lacks the capabilities to perform any actions (such as file writes or network requests) that could be exploited through this vector. 1. Ingestion points: Reads .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md (identified in SKILL.md). 2. Boundary markers: None specified. 3. Capability inventory: No tool usage or script execution patterns found across provided files. 4. Sanitization: No specific sanitization measures mentioned for ingested context.

onboarding