The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes information retrieved from external APIs (Apollo, LinkedIn, Akta, Strale) which represents an attack surface for indirect prompt injection.\n- Ingestion points: Results returned from the sandbase_call_tool function as seen in the workflow of SKILL.md.\n- Boundary markers: The skill does not explicitly instruct the agent to use specific delimiters or ignore embedded instructions within the fetched data.\n- Capability inventory: Uses sandbase_call_tool to interact with multiple external data providers for enrichment and lookup tasks.\n- Sanitization: No explicit sanitization or validation of the enrichment data is mentioned in the instructions.

data-enrichment