ticket-states

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external ticket tracker which could contain malicious instructions.
  • Ingestion points: The agent is instructed to read and modify ticket briefs, comments, and notes.
  • Boundary markers: There are no instructions to use delimiters or ignore embedded commands within the ticket data.
  • Capability inventory: The skill uses shell-based commands (bd update, bd comments add) to write data back to the system.
  • Sanitization: The skill does not prescribe escaping or sanitization of the ticket content before it is interpolated into shell command arguments (e.g., bd update <id> --append-notes "<text>").
  • [COMMAND_EXECUTION]: The skill provides instructions to execute a command-line utility named bd (Beads) to manage ticket states and metadata.
  • Evidence: Examples include bd update, bd comments add, bd list, and bd ready. These are core to the skill's functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 09:21 AM