improve-operations
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows standard operational procedures for analyzing business workflows. It identifies bottlenecks and suggests improvements based on local data.
- [DATA_EXPOSURE]: The skill reads data from the ".business/" directory, including context, metrics, and plans. This is consistent with its stated purpose of operational diagnosis and does not involve unauthorized access to sensitive system or user configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes "customer evidence" which could originate from untrusted external sources. While this presents an ingestion point for indirect prompt injection, the skill includes explicit constraints against making live changes without authorization, mitigating the risk of automated exploitation.
Audit Metadata