surf-tenant-rename
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies extensively on shell command generation, using tools such as
git,kubectl,sed,sops,age-keygen, andglab. These commands directly incorporate user-defined variables (<old-name>and<new-name>) to perform file modifications and system configuration changes. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. The user-provided parameters
[old-name]and[new-name]are interpolated into shell commands (e.g.,sed -i 's/<old-name>/<new-name>/g') without instructions for sanitization or validation. A malicious user could provide input containing shell metacharacters to execute arbitrary commands. - [DATA_EXPOSURE]: The workflow involves decrypting secrets and writing them to a temporary file (
/tmp/secrets-backup.yaml). Although this is a step in a migration process, it temporarily exposes sensitive information in a common system directory.
Audit Metadata