moai-change-logger
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface.
- Ingestion points: Monitors file system modifications and Git repository activity (commits, branch history, and status) as described in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are defined in the provided logic for processing file changes or git messages.
- Capability inventory: The skill is permitted to use
Bash,Write,WebSearch, andWebFetchtools. - Sanitization: No content sanitization or validation is indicated for data read from files or git logs before processing.
- [COMMAND_EXECUTION]: The skill is granted
Bashpermissions and includes logic to track command history (track_command_history). This functionality creates a risk of logging sensitive data if shell commands containing secrets are captured in persistent audit trails.
Audit Metadata