The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches protocol specifications from https://a2a-protocol.org/latest/specification/ and performs web searches to find reference architectures and community patterns.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external websites and search results.
Ingestion points: Data enters the agent context through WebFetch (from a2a-protocol.org) and WebSearch (community patterns) as directed in SKILL.md.
Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions found within the fetched content.
Capability inventory: The agent has access to sensitive tools including Bash, Write, and Edit which could be misused if the fetched data contains malicious instructions.
Sanitization: No validation or sanitization of the external content is described before it is processed by the agent.

a2a-dev-patterns