groove-utilities-memory-promises
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes commands using the
beansCLI tool to manage milestones, epics, and tasks. These operations are scoped to the specific tool as defined in the skill's configuration. - [INDIRECT_PROMPT_INJECTION]: The skill accepts text from
$ARGUMENTSand interactive user prompts to populate task titles and descriptions, creating a surface for indirect instructions to be processed by the agent. - Ingestion points: User-provided strings via
$ARGUMENTSandAskUserQuestionresults for task titles and context (SKILL.md). - Boundary markers: None identified in the prompt templates.
- Capability inventory: The skill possesses
beansCLI execution capabilities (create, update, list) and filesystemReadaccess (SKILL.md). - Sanitization: No explicit sanitization or escaping of the user-provided content is defined before it is passed to the task management system.
Audit Metadata