The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill interacts with external ServiceNow tables, which creates a potential surface for indirect prompt injection if those tables contain malicious content.
Ingestion points: The skill utilizes SN-Query-Table and SN-List-CmdbCis to ingest data from tables such as cmdb_ci and sys_db_object (documented in SKILL.md).
Boundary markers: There are no specific delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the retrieved CI data.
Capability inventory: The skill possesses write/update capabilities via SN-Create-Record and SN-Update-Record (documented in SKILL.md), allowing the agent to modify the CMDB based on interpreted data.
Sanitization: The instructions do not include explicit steps for validating or sanitizing the content retrieved from ServiceNow before processing it.

ci-discovery