The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from external systems, which is a potential surface for indirect prompt injection.
Ingestion points: Text data is ingested from the value field in sys_journal_field (comments and work notes) and the short_description field in sn_proc_case in Steps 1 and 2.
Boundary markers: The skill does not provide specific delimiters or instructions to ignore embedded commands within the ingested text during the summarization process.
Capability inventory: The skill possesses capabilities for network operations (via ServiceNow REST API and MCP tools) and shell execution (via the Bash tool listed in frontmatter).
Sanitization: No explicit sanitization or filtering logic is described for the retrieved journal entries or case descriptions before they are interpolated into the summarization prompt.

procurement-summarization