The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the clay command-line interface to perform its tasks. It explicitly instructs the agent to run commands such as clay whoami, clay routines list, clay routines runs start, and clay search to verify the environment and execute data enrichment workflows.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, creating a potential vector for indirect prompt injection.
Ingestion points: In Step 1, the skill ingests user-supplied CSV files or pasted lists containing emails, names, and company details.
Boundary markers: The instructions lack specific requirements for using boundary markers (e.g., XML tags or clear delimiters) when the agent processes the input records.
Capability inventory: The skill has the capability to execute shell commands (via the Clay CLI) and perform network-based data enrichment through the Clay platform.
Sanitization: The skill employs "deterministic screens" and classification enums to process data, but it does not specify rigorous sanitization or escaping of the input strings before they are passed as arguments to CLI tools or search queries.
[EXTERNAL_DOWNLOADS]: The skill performs person and company enrichment by communicating with the Clay cloud platform. This involves sending signup data to external APIs for resolution and scoring, which is the intended core functionality of the skill.

enrich-signup-users