The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content from external websites based on user input, which serves as a potential vector for indirect prompt injection attacks.
Ingestion points: The skill ingests untrusted data from web_search results and content fetched directly from https://www.similarweb.com/website/[domain]/ in Step 1.
Boundary markers: The instructions do not define explicit boundary markers or delimiters (such as XML tags) to isolate external web content from the agent's instructional context.
Capability inventory: The skill utilizes web_search and web_fetch capabilities across all operational scripts to gather information.
Sanitization: There is no evidence of sanitization, filtering, or validation logic applied to the ingested external content before it is interpreted by the agent.

traffic-analyzer