skills/zenobi-us/dotfiles/jira/Gen Agent Trust Hub

jira

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHCOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (HIGH): In scripts/get_ticket_summary.sh, the $TICKET_ID variable is interpolated into a double-quoted string within a subshell: $(... "$TICKET_ID" ...). This allows an attacker to execute arbitrary code via command substitution (e.g., passing $(whoami) as an argument).
  • Indirect Prompt Injection (LOW): The skill fetches and displays Jira ticket summaries and descriptions without sanitization. 1. Ingestion points: scripts/get_ticket_summary.sh fetches Jira issue fields. 2. Boundary markers: No delimiters are used to wrap external content. 3. Capability inventory: The scripts use mcporter for Jira API calls. 4. Sanitization: No escaping or filtering of Jira content is performed.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:13 PM