The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes account data from external CSV or CRM exports, which is then interpolated into shell commands for the 'clay' CLI tool.
Ingestion points: The skill accepts account lists as CSV or CRM exports provided by the user (described in SKILL.md).
Capability inventory: The skill uses shell execution to run clay routines runs start which processes the input data (SKILL.md, references/enrichment-mechanics.md).
Boundary markers: The skill does not explicitly mention the use of delimiters to isolate untrusted data when passing it to the CLI tool, though it does instruct the agent to deduplicate and validate domains.
Sanitization: The skill implements identity validation, public-suffix-aware domain normalization, and DNS/HTTP probes to verify domains before enrichment.
[COMMAND_EXECUTION]: The skill executes shell commands using the 'clay' CLI tool to perform account enrichment and check workspace status.
Evidence: The instructions include calls to clay whoami, clay routines get, and clay routines runs start (SKILL.md).
Context: These commands are essential for the skill's primary function of interacting with the Clay enrichment routines and are considered vendor-specific tool usage.

enrich-account-list