mz-debug-freshness
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a well-documented technical guide for debugging database synchronization issues. It leverages platform-specific introspection features to analyze dataflow costs and ingestion status without performing any destructive or unauthorized actions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the database system catalog, which could theoretically contain malicious instructions.
- Ingestion points: System catalog metadata, source/sink error messages, and view definitions are retrieved via the
query_system_catalogandquerytools as described in SKILL.md and references/attribution.md. - Boundary markers: The instructions focus on structured analysis of specific fields but lack explicit boundary markers or instructions for the agent to ignore potentially malicious content within free-text fields like error messages or SQL definitions.
- Capability inventory: The skill is strictly limited to read-only database queries and lacks capabilities for file system modification, network exfiltration, or shell command execution.
- Sanitization: No explicit sanitization or escaping of database-derived content is performed before it is incorporated into the agent's context or the final report.
Audit Metadata