The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various CLI commands using the clay tool (e.g., clay whoami, clay workflows create). These commands are used for environment verification and managing data processing workflows within the vendor's ecosystem.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from an external local file referred to as an "answer sheet." This process lacks explicit instruction for boundary enforcement or input sanitization, creating a potential vector for indirect prompt injection if the file content is untrusted.
Ingestion points: Loading external data from an "answer sheet" file as described in the SKILL.md file.
Boundary markers: No specific delimiters or warnings to ignore embedded instructions are provided for the file ingestion process.
Capability inventory: The skill utilizes the clay CLI, calls external actions via the Clay platform, and possesses the capability to write identifiers back to local files.
Sanitization: There are no instructions for sanitizing or validating the content loaded from the external file before it is used in the agent's context.

headcount-growth