The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external records which could be influenced by third parties (customers or external users).
Ingestion points: The skill retrieves data from sn_customerservice_case (description, close_notes) and sys_journal_field (work_notes, comments) as shown in Step 1, Step 2, and Step 3 of the procedure in SKILL.md.
Boundary markers: Absent. The instructions do not provide specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the retrieved case data.
Capability inventory: The skill utilizes SN-Create-Record and SN-Update-Record to modify the knowledge base, uses SN-Execute-Background-Script for batch operations, and has access to the Bash tool for general system operations.
Sanitization: Absent. There is no evidence of specific sanitization, escaping, or filtering of the ingested case content before it is interpolated into article generation prompts.

csm-kb-generation