The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which presents a potential injection surface.
Ingestion points: Data is retrieved from external DEX API endpoints via the invoke_api_endpoint tool as described in SKILL.md.
Boundary markers: The skill uses a structured Report template and a required Evidence receipt to format findings, which helps delimit data from instructions.
Capability inventory: The skill uses search_tools and invoke_api_endpoint. It lacks capabilities for local file writing, persistence, or high-privilege command execution.
Sanitization: The procedure mandates the use of validate_task_result to verify the structure of the workflow result before presentation.

hive-dex-pool-analysis