The Agent Skills Directory

[SAFE]: The skill is purely informational and provides strategic advice for SEO. It does not invoke any system tools, execute scripts, or perform network operations.- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an ingestion surface for potential indirect prompt injection. Evidence Chain: 1. Ingestion points: The skill instructs the agent to read .agents/product-marketing.md and related context files in SKILL.md. 2. Boundary markers: No delimiters or specific safety instructions are provided for these external files. 3. Capability inventory: No high-risk capabilities such as file writes, network requests, or shell execution are present. 4. Sanitization: No sanitization of input data is performed. Despite the ingestion surface, the lack of dangerous capabilities makes this surface low-risk and safe for the agent to process.

programmatic-seo