qa-jira-integration

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, specifically outputs from the qa-bug-ticket-creator and qa-task-creator skills, to populate Jira issue fields such as summary, description, and comments.
  • Ingestion points: SKILL.md specifies receiving bug reports and task definitions from other skills.
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate the external content from the agent's internal instructions during the mapping process.
  • Capability inventory: The skill possesses capabilities to create, update, and transition issues via the Jira REST API, as well as add attachments and comments.
  • Sanitization: While the skill notes that JQL queries should be safe from injection, there is no explicit mention of sanitizing or escaping the content used in the Atlassian Document Format (ADF) descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-jira-integration