The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Web search results from scripts/search and page content from scripts/content enter the agent context.
Boundary markers: The skill uses simple text delimiters (e.g., '--- Result 1 ---') to separate content, which provides minimal protection against adversarial input.
Capability inventory: The skill is designed for reading and extraction; no dangerous write or execution capabilities were identified in the provided documentation.
Sanitization: There is no evidence of sanitization or filtering of fetched content to prevent instructions from being interpreted by the LLM.

brave-search