skills/junoh-moon/skills/jira-write/Gen Agent Trust Hub

jira-write

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill possesses write capabilities and processes untrusted data from external sources, creating a high-risk surface for indirect prompt injection. * Ingestion points: Data retrieved from Jira via JQL (sprints, epics) and user-provided text for summaries and descriptions (SKILL.md). * Boundary markers: Absent. The instructions do not define delimiters to separate system instructions from the untrusted data being processed. * Capability inventory: createJiraIssue, editJiraIssue, transitionJiraIssue, and addCommentToJiraIssue (all in SKILL.md). * Sanitization: Absent. There is no evidence of input validation, escaping, or filtering of content retrieved from Jira or provided by the user.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 07:51 AM