mz-limits-test
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external content (user instructions and local files) to generate executable code.
- Ingestion points: User-provided descriptions of stress tests and the content of the
test/limits/mzcompose.pyfile. - Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands in the data it processes.
- Capability inventory: The skill generates SQL queries and shell commands (via the
mzcomposeframework) that can modify system settings (ALTER SYSTEM) and perform database operations. - Sanitization: Absent; no validation or escaping is applied to user-supplied data before it is interpolated into the generated test code.
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the vendor-specific
bin/mzcomposetool and to generate shell commands via thepostgres-executeDSL. These operations are within the scope of the skill's primary purpose of database testing.
Audit Metadata