groove-utilities-task-config

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing data from a user-controlled local file.
  • Ingestion points: Reads frontmatter from .groove/index.md (specifically the tasks: key).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate data from system instructions during processing.
  • Capability inventory: The skill manifest grants access to a high-privilege toolset including Write, Edit, and Bash (allowing access to git, gh, and npx).
  • Sanitization: No sanitization or content validation is specified beyond checking for a set of four allowed backend values.
  • [COMMAND_EXECUTION]: The skill's manifest requests broad access to several CLI tools via Bash (including git, gh, linear, beans, and npx). While these appear consistent with managing task backends for the 'groove' utility suite, they provide a powerful interface for system interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 09:04 AM