work-on-ticket

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it processes data retrieved from external Jira tickets.
  • Ingestion points: The scripts fetch-ticket.ts and start-work.ts fetch summary and description fields from the Jira API.
  • Boundary markers: No delimiters or instructions are provided to the agent to treat the fetched content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill has the capability to execute Git branch operations (creation and pushing) and update Jira ticket statuses.
  • Sanitization: The fetched Jira ticket content is displayed and processed without visible sanitization or validation.
  • [COMMAND_EXECUTION]: The skill performs Git and Jira operations using ticket-derived metadata (such as summaries and keys). While these are intended functions, there is a risk of command injection if the internal library implementation does not correctly sanitize these inputs before execution.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of dependencies from the official NPM registry, which is a well-known and trusted service.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:40 AM