The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection.
Ingestion points: Data is pulled from external sources using WebSearch and from existing local files in directories like competitive/, competitors/, and research/ via the @file syntax.
Boundary markers: The instructions lack delimiters or specific directives to ignore or isolate instructions that might be embedded in the retrieved competitive data.
Capability inventory: The skill utilizes file read/write operations (specifically saving to the competitive/ folder) and network capabilities via WebSearch tools.
Sanitization: There is no evidence of sanitization or validation of the content fetched from the web or read from files before it is processed by the agent's logic.

competitive-analysis