release-notes-generation

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform REST API operations, specifically GET and POST requests, to interact with ServiceNow table APIs for retrieving and updating records.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it retrieves data from external ServiceNow tickets and incorporates it into agent-generated content.
  • Ingestion points: Data is queried from change_request, rm_story, rm_defect, and incident tables using the SN-Query-Table tool and REST API calls (SKILL.md Steps 2-5).
  • Boundary markers: None. External data is interpolated directly into the release notes document template (SKILL.md Step 6) without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill can create new records in the knowledge base (SN-Create-Record) and update existing release records (SN-Update-Record).
  • Sanitization: There is no evidence of validation or sanitization of the content retrieved from ticket fields before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:34 PM
Security Audit — agent-trust-hub — release-notes-generation