The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of clay CLI commands to list, create, and manage routines within the user's workspace. These operations are performed in the local shell environment and are essential for the skill's functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes results from routine runs using the clay routines runs get command. Since these results may contain data from external sources (e.g., email enrichers, domain lookups), they represent a surface for indirect prompt injection.\n
Ingestion points: Data returned from enrichment routines is ingested into the agent's context through run status and result queries.\n
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when handling routine output, which could lead the agent to follow instructions embedded in the data.\n
Capability inventory: The agent has the ability to execute CLI commands for workspace management, credit balance checks, and routine execution.\n
Sanitization: There is no evidence of sanitization, filtering, or validation applied to the external data before it is presented to or processed by the agent.

routines