maestro-tools-register
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by processing untrusted data without explicit sanitization or boundary enforcement.
- Ingestion points: User input via the
$ARGUMENTSvariable and the contents of existing 'knowhow' documents during extraction or promotion modes. - Boundary markers: Absent. The instructions do not define clear delimiters or use 'ignore' instructions for data being interpolated into shell commands or YAML frontmatter.
- Capability inventory: The skill is granted access to high-capability tools including
Bash,Write,Edit, andGrep, which allow for system command execution and file system modification. - Sanitization: There is no evidence of sanitization, escaping, or validation logic for user-provided strings before they are incorporated into
maestroCLI commands or written to the file system.
Audit Metadata