Skills
skills/odyssey4me/agent-skills/jira/Gen Agent Trust Hub

jira

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external Jira instances (issue summaries, descriptions, comments, and user profiles) which could contain malicious instructions. This represents an indirect prompt injection surface inherent to tools that ingest external collaborative data.
  • Ingestion points: scripts/jira.py (via get_issue, get_comments, search_issues, and resolve_user).
  • Boundary markers: No explicit delimiters or isolation instructions are implemented in the scripts to distinguish external data from system instructions.
  • Capability inventory: scripts/jira.py supports creating/updating issues, adding comments, and performing workflow transitions.
  • Sanitization: Data is structured for the Jira API (e.g., Atlassian Document Format) but is not sanitized or filtered for potential prompt injection content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:21 PM
Security Audit — agent-trust-hub — jira