The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted information from web search results to generate its reports, representing an indirect prompt injection surface.
Ingestion points: External data enters the agent context via web_search results (SKILL.md).
Boundary markers: Absent; the instructions do not require the agent to use specific delimiters when processing web content.
Capability inventory: The skill utilizes web_search and has the ability to write result files.
Sanitization: No specific sanitization or filtering of external content is mentioned before it is included in the output report.

trade-screen