The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: This skill utilizes data from web searches and local documents, which creates a potential surface for indirect prompt injection.
Ingestion points: Untrusted data is ingested via the WebSearch tool and by reading files from paths like market/, research/, strategy/, and analysis/.
Boundary markers: The instructions do not define any delimiters or provide explicit directives to the agent to ignore or isolate instructions found within the ingested data.
Capability inventory: The skill is capable of performing network-based web searches, reading local files, and writing generated markdown files to the local file system.
Sanitization: There is no documentation of sanitization, validation, or escaping of the external data gathered from the web or from existing research files before it is processed by the agent.

market-analysis