rhdh-jira-sprint-plan

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the acli Jira CLI tool to perform bulk reads of boards, sprints, and work items. These commands are executed via shell blocks in the workflow to retrieve project management data.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from Jira issue fields (summaries, descriptions, priorities) without explicit sanitization or boundary markers.
  • Ingestion points: Data is retrieved from Jira work items in workflows/plan-sprint.md using acli jira workitem search across multiple steps (Carryover, Velocity, Ready-for-planning, etc.).
  • Boundary markers: The workflow does not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded within the Jira fields when generating the final report.
  • Capability inventory: The skill has the capability to execute shell commands (acli) and interact with other internal skills (/rhdh-jira-api, /rhdh-jira-update).
  • Sanitization: There is no evidence of escaping, filtering, or validation of the external content retrieved from Jira before it is interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 04:03 PM
Security Audit — agent-trust-hub — rhdh-jira-sprint-plan