The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill incorporates external data ingestion by fetching specifications and searching GitHub for implementation examples, creating a potential vector for instructions embedded in remote content to influence the agent.
Ingestion points: The skill instructs the agent to use WebFetch for https://a2a-protocol.org/latest/specification/ and WebSearch for a2aproject error codes and samples on GitHub.
Boundary markers: There are no instructions providing delimiters or specific guidance to ignore potential commands within the fetched external data.
Capability inventory: The skill utilizes Bash, Write, Edit, and Grep tools, which could be used to modify the environment or local files based on instructions found in the external documentation.
Sanitization: The instructions do not specify any validation, filtering, or sanitization steps for the data retrieved from external URLs or search results.

a2a-error-handling