The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted external data, which creates a surface for indirect prompt injection attacks.
Ingestion points: The skill instructions in SKILL.md direct the agent to "Analyze if this webpage implements structured data" and "Verify the rendered HTML and HTTP response".
Boundary markers: There are no specific instructions or delimiters provided to help the agent distinguish between its core instructions and content found within the analyzed HTML/HTTP responses.
Capability inventory: The skill grants the agent the ability to perform code reviews, generate code fixes, and provide explanations, which could be influenced by malicious content in the target pages.
Sanitization: The instructions do not mention any sanitization, filtering, or escaping of the external data before it is processed by the agent.

structured-data