configure
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it reads and processes the
~/.bitwize-music/config.yamlfile and user-provided paths while possessing sensitive capabilities likeBashandWritetools. - Ingestion points: The skill reads configuration data from
~/.bitwize-music/config.yaml(File: SKILL.md) and accepts various paths and settings from user input via theAskUserQuestiontool. - Boundary markers: Absent; the instructions do not specify any delimiters or warnings to ignore embedded instructions when reading the config file.
- Capability inventory: The skill is granted
Bash,Write,Read,Glob, andAskUserQuestiontools (File: SKILL.md). - Sanitization: Absent; the skill performs YAML validation but does not explicitly sanitize content for prompt or command injection.
- COMMAND_EXECUTION (SAFE): The skill is granted the
Bashtool to perform file system operations like directory creation and file existence checks. These are standard operations for a configuration utility and do not pose a high risk in this context.
Audit Metadata