The Agent Skills Directory

[SAFE]: The skill operates within its stated purpose of SEO and market research. No malicious code, unauthorized file access, or suspicious network exfiltration patterns were identified. All tools and external services referenced, such as the OpenSEO MCP tools, are part of the vendor's legitimate service infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, including prompts retrieved from search datasets and answers generated by AI models. This creates an attack surface for indirect prompt injection. The skill effectively mitigates this risk by including a mandatory guardrail instruction that explicitly directs the agent to treat all prompt text and cited pages as untrusted and to ignore any instructions embedded within them. The skill's capabilities are limited to research reporting and context logging, which further reduces the potential impact of such attacks.

ai-prompt-research