The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as LinkedIn, Apollo, and Strale via the sandbase_call_tool capability. This creates an ingestion point for untrusted content that could contain instructions designed to influence the agent's behavior.
Ingestion points: External data retrieved from Apollo, Strale, LinkedIn, and Akta as described in SKILL.md and references/sandbase-api-map.md.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded content within the tool outputs.
Capability inventory: The agent uses sandbase_describe_tool and sandbase_call_tool to perform research and data synthesis.
Sanitization: No explicit sanitization, escaping, or filtering of the external API responses is mentioned in the provided instructions.

data-enrichment