The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and templates. It does not include any scripts (.py, .js, .sh), configuration files that trigger execution, or tool definitions that grant the agent operational capabilities.
[SAFE]: No evidence of prompt injection or attempts to bypass safety guardrails was found in the instructions or metadata.
[SAFE]: All external links and references target legitimate documentation, research papers, or well-known technology blogs (e.g., Google Search Central, Princeton research, specialized SEO blogs). No suspicious or obfuscated URLs were detected.
[INDIRECT_PROMPT_INJECTION]: The skill instructions include an ingestion point where the agent reads local context files (e.g., .agents/product-marketing.md in SKILL.md). However, because the skill provides no functional capabilities or tools (Capability Inventory: None), there is no pathway for untrusted data to execute malicious actions or exfiltrate data. Boundary markers and sanitization are absent as the skill is primarily focused on providing conversational advice based on static templates.

ai-seo