backup
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute various commands for repository configuration, file monitoring with fswatch, and GitHub interactions using the gh CLI.
- [DATA_EXFILTRATION]: The skill is designed to synchronize local recordings to a remote GitHub repository. It transmits local data off-system to a well-known service (GitHub) as its primary purpose.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection. * Ingestion points: User-provided repository names, intervals, and responses to AskUserQuestion. * Boundary markers: None specified to separate user data from commands. * Capability inventory: Access to Bash, Glob, and Write tools. * Sanitization: The skill description does not specify validation or escaping for user-supplied arguments used in shell commands.
Audit Metadata