groove-utilities-task-analyse

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes command-line utilities including gh, linear, and a tool named beans. It also calls a local workspace script at skills/groove-utilities-task-list/scripts/list-tasks-by-priority.sh. These commands are used as intended to retrieve task metadata for summarization.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates external task data into the agent's context.
  • Ingestion points: Task titles, descriptions, and 'Summary of Changes' sections are fetched from GitHub, Linear, and the Beans backend.
  • Boundary markers: The skill does not define specific delimiters or isolation instructions to prevent the agent from obeying instructions embedded in the task content.
  • Capability inventory: The skill has permissions for Bash, Write, Edit, and Read tools, which increases the potential impact of an injection attack.
  • Sanitization: No sanitization or content validation is performed on the task data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 09:04 AM