rhdh-jira-authoring

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The file references/grill.md instructs the agent to execute git diff --name-only HEAD~3 to inspect recently modified files. This command is used to automatically infer and suggest Jira components based on the current development context, which is a standard and safe operation for a developer-focused agent.
  • [COMMAND_EXECUTION]: The references/duplicates.md file defines a search pattern using the acli jira workitem search command. This is used for read-only duplicate detection before creating new work items, helping maintain Jira data integrity.
  • [PROMPT_INJECTION]: The skill ingests user-provided text to populate Jira templates in assets/templates/. While this creates a surface for indirect prompt injection, the skill mitigates this by enforcing strict templates and requiring validation before issue creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 11:10 AM
Security Audit — agent-trust-hub — rhdh-jira-authoring