groove-admin-config

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing external data.
  • Ingestion points: User-provided values from AskUserQuestion and existing configuration data from .groove/index.md.
  • Boundary markers: Absent; inputs are interpolated into file templates without delimiters or ignore instructions.
  • Capability inventory: The skill utilizes Write and Edit tools for file modification, and restricted Bash commands for git, github, and npx operations.
  • Sanitization: There is no evidence of input validation or escaping for the user-supplied configuration keys or values.
  • [EXTERNAL_DOWNLOADS]: The skill is authorized to use npx via bash, which can lead to the download and execution of packages from the npm registry during the configuration process or subsequent steps.
  • [COMMAND_EXECUTION]: The skill defines a restricted set of bash commands (git, beans, gh, linear, npx, mkdir). These commands are consistent with the tool's administrative purpose and the author's infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 08:34 PM