The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using the hubspot CLI, jq, and system utilities (date, column) to fetch and format CRM data. These operations are consistent with the skill's primary purpose and use the vendor's official toolset.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from HubSpot CRM records, such as deal names and property values, which serves as a potential vector for indirect prompt injection.
Ingestion points: Data enters the agent context through hubspot objects search and hubspot reports fetch-dataset calls described in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from interpreting record content as commands.
Capability inventory: The skill has the ability to execute shell commands and write to the local file system (e.g., creating /tmp/owners.tsv).
Sanitization: While jq is used for numeric filtering and aggregation, descriptive text fields from the CRM are included in the output without specific sanitization or escaping.

sales-reporting