mpm-ticket-view

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the aitrackdown CLI tool as a fallback mechanism for ticketing operations. Commands mentioned include aitrackdown status tasks, aitrackdown show, and aitrackdown transition.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing external data without explicit sanitization or boundary markers.
  • Ingestion points: Untrusted data enters the agent context via ticketing platforms (Linear, GitHub, JIRA) through tools such as ticket_read, ticket_list, and ticket_comment.
  • Boundary markers: The instructions lack delimiters or warnings to ignore embedded instructions within the ticket data.
  • Capability inventory: The agent has the authority to perform write operations, including ticket_transition, ticket_update, and ticket_comment, as well as shell command execution via the aitrackdown CLI.
  • Sanitization: No sanitization or validation protocols are defined for the content fetched from external ticketing systems.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 02:30 PM
Security Audit — agent-trust-hub — mpm-ticket-view