The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data from the web, which introduces a surface for indirect prompt injection attacks.\n- Ingestion points: The agent is instructed to 'Read the top 10 results' from Google searches for target keywords (SKILL.md).\n- Boundary markers: The prompt lacks specific delimiters or guardrail instructions to prevent the agent from following malicious instructions that might be hidden in the external web pages it reads.\n- Capability inventory: The skill's primary capabilities include search tool execution, reading local reference documentation, and providing structured output to subsequent writing tasks.\n- Sanitization: There are no explicit mechanisms mentioned to sanitize, validate, or filter the content retrieved from external search results before it is processed by the agent.

content-brief