The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted third-party content from search engine results.\n
Ingestion points: Data retrieved from SerpAPI (Google, Bing, etc.) such as organic snippets, "People Also Ask" questions, and AI Overviews as described in SKILL.md.\n
Boundary markers: Absent. There are no instructions for the agent to treat the search result content as untrusted or to ignore instructions embedded within the snippets.\n
Capability inventory: The skill allows an agent to read search results. The documentation refers to other tools like review-management or local-landing-pages that may have writing capabilities.\n
Sanitization: Absent. No specific sanitization or filtering of search result content is mentioned in the instructions.\n- [NO_CODE]: This skill consists exclusively of markdown documentation and instructions, with no executable code, scripts, or binaries provided.

serpapi-tool