The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources including LinkedIn, Twitter, and Google News.
Ingestion points: Data enters the agent's context through results returned by sandbase_call_tool from various external APIs (SKILL.md).
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate external data from the system prompt (SKILL.md).
Capability inventory: The skill uses vendor-provided gateway tools sandbase_describe_tool and sandbase_call_tool for data retrieval (SKILL.md, references/sandbase-api-map.md).
Sanitization: There are no instructions for sanitizing or validating the content retrieved from external sources before it is processed by the agent.

sales-intelligence