Skills
Navigate
skills/happy-technologies-llc/happy-platform-skills/release-notes-generation/Gen Agent Trust Hub

release-notes-generation

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill aggregates untrusted data from various ServiceNow tables and interpolates it into an AI-generated release notes document.\n
  • Ingestion points: Data is retrieved from fields like description, short_description, and acceptance_criteria in the change_request, rm_story, and rm_defect tables (SKILL.md, Steps 2-5).\n
  • Boundary markers: The skill does not define specific delimiters or "ignore instructions" warnings for the data being processed in the generation step (SKILL.md, Step 6).\n
  • Capability inventory: The agent can publish content via SN-Create-Record and SN-Update-Record (SKILL.md, Steps 7-8).\n
  • Sanitization: No validation or sanitization steps are defined for the content retrieved from external records.\n- [COMMAND_EXECUTION]: The skill instructions include Bash commands for interacting with ServiceNow REST APIs.\n
  • These commands target official ServiceNow table APIs (/api/now/table/...) to retrieve and update records.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:46 AM