The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface due to its core functionality of processing external, potentially untrusted data.
Ingestion points: The skill utilizes tools such as site_audit, serp_analysis, search_neilpatel_blog, and content_ideas to fetch and analyze content from external websites and search results.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to treat tool-returned content as data rather than commands, which is a common practice to mitigate injection risks.
Capability inventory: The agent has permissions to perform actions based on this data, including generating articles (generate_article), creating projects, and modifying keyword lists.
Sanitization: There is no evidence of pre-processing or sanitization steps described in the instructions to filter out potentially malicious instructions embedded in the ingested data.

seo-foundations